© 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. 102286
    Prev
    Next
    INDEX
    Explanations

    driven by

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

    legal rights or consent

    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
     것은
    0.47
    儁
    0.46
    ם
    0.45
     सेवानिव
    0.44
     নিঃসন্দে
    0.44
     представляет
    0.44
    ждение
    0.43
     대해서
    0.43
     esfuer
    0.43
    ची
    0.43
    POSITIVE LOGITS
    `<
    0.51
    Smiling
    0.50
    Smile
    0.47
    ILA
    0.47
    ?
    0.47
    Side
    0.46
     smiling
    0.46
    AAAA
    0.46
     ambos
    0.44
    $?
    0.44
    Activations Density 0.002%

    No Known Activations