© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100364
    Prev
    Next
    INDEX
    Explanations

    public declarations

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

    The neuron fires on the access modifier “public” (i.e. the start of class, method, or function declarations).

    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
     and
    -1.73
     \&
    -1.47
    zob
    -1.36
     some
    -1.35
    zyści
    -1.30
    patine
    -1.27
    angeran
    -1.27
     finds
    -1.27
     desnuda
    -1.26
    ...),
    -1.25
    POSITIVE LOGITS
     prouver
    1.40
    >
    1.32
    是
    1.30
     complètes
    1.29
    y
    1.23
     personnalisées
    1.22
     insectes
    1.22
     passent
    1.20
     -
    1.20
    oooo
    1.20
    Activations Density 0.019%

    No Known Activations