© 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. 111344
    Prev
    Next
    INDEX
    Explanations

    nation, want, base, bone, erode

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

    isolation and funny

    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
     stunted
    0.55
     ち
    0.51
     quenching
    0.51
     gimmick
    0.51
     gimm
    0.48
     breather
    0.47
    ウィン
    0.46
    stocked
    0.46
     mischievous
    0.46
     toned
    0.45
    POSITIVE LOGITS
    Š
    0.44
    alke
    0.43
    elipe
    0.43
    alaa
    0.41
    ovima
    0.40
    edas
    0.40
    誢
    0.40
     अकादमी
    0.40
     만들
    0.39
    azoline
    0.39
    Activations Density 0.000%

    No Known Activations