© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111935
    Prev
    Next
    INDEX
    Explanations

    html tags and email addresses

    np_acts-logits-general · gemini-2.5-flash-lite

    the hash symbol (#) used as an anchor identifier in markdown image syntax.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron consistently fires on the “#” token, i.e. the hash symbol used in markup (e.g. as an ID/anchor marker).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -1.38
    ]
    -1.35
     tormenta
    -1.34
     momentan
    -1.34
    –
    -1.28
     schilder
    -1.27
    ⑊
    -1.23
    lizard
    -1.21
    cised
    -1.20
    isiert
    -1.20
    POSITIVE LOGITS
     from
    1.26
    UIButton
    1.25
     this
    1.15
    impresa
    1.14
    czną
    1.13
     chanteuse
    1.13
    大胆
    1.11
    信念
    1.11
    ₁(
    1.11
     if
    1.11
    Activations Density 0.032%

    No Known Activations