© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21494
    Prev
    Next
    INDEX
    Explanations

    masked or redacted content

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

    important or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ︵
    0.63
    >
    0.63
     equivoc
    0.61
     algéb
    0.58
    fläche
    0.57
    <0x97>
    0.57
     anderer
    0.57
     outros
    0.56
     verá
    0.56
    <unused2162>
    0.56
    POSITIVE LOGITS
    ️⃣
    0.75
     Depending
    0.75
     **
    0.74
    ******
    0.71
     (*
    0.70
     *
    0.66
     $*$
    0.65
     (
    0.63
    ********
    0.62
     Applies
    0.62
    Activations Density 0.009%

    No Known Activations