© 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. 188296
    Prev
    Next
    INDEX
    Explanations

    He, biblical perspective, desert

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

    pollen collection, access, label, jump

    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
    ﺰ
    0.49
     outcast
    0.48
    Moss
    0.45
     Dyna
    0.44
    𝓑
    0.44
    jw
    0.44
    чными
    0.43
     jigsaw
    0.43
    чные
    0.43
     тыся
    0.43
    POSITIVE LOGITS
    内在
    0.47
     sitt
    0.46
    とする
    0.44
    opend
    0.44
    +}$,
    0.43
    imoto
    0.42
    ａ
    0.42
     to
    0.42
    apu
    0.41
    㷫
    0.41
    Activations Density 0.000%

    No Known Activations