© 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. 74382
    Prev
    Next
    INDEX
    Explanations

    before federal laws

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

    specific entities and topics

    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
     दुःख
    0.54
     думать
    0.53
     maliciously
    0.49
    $=\
    0.47
     органов
    0.46
     Verificar
    0.46
    दत
    0.45
    :_
    0.45
     ساعت
    0.44
     Şubat
    0.44
    POSITIVE LOGITS
    賽
    0.47
    endre
    0.46
    τες
    0.45
     Herzegovina
    0.44
    ṇa
    0.43
    igny
    0.42
    ă
    0.42
    قيم
    0.41
    isher
    0.40
    נה
    0.40
    Activations Density 0.001%

    No Known Activations