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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 134
    Prev
    Next
    INDEX
    Explanations

    Peter Rost

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

    The neuron detects long sequences of repeated dash characters (i.e. horizontal divider lines made of hyphens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.24
    づけ
    -1.20
     focused
    -1.15
     of
    -1.08
    おわりに
    -1.07
     unusual
    -1.04
    感を
    -1.02
     identify
    -1.02
     επίσης
    -1.02
     ванной
    -0.99
    POSITIVE LOGITS
    ebly
    1.13
    (),
    1.10
    #,
    1.09
     certains
    1.08
     kostenlose
    1.07
    uding
    1.07
    ary
    1.07
    ❋
    1.06
    中には
    1.05
    靦
    1.05
    Activations Density 0.001%

    No Known Activations