© 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. 200157
    Prev
    Next
    INDEX
    Explanations

    early on, bring those, atomic bombs

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

    integrity=" links

    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
    お客様
    0.41
    のお客様
    0.39
     '|')
    0.39
     ត
    0.38
    pressed
    0.38
    客様
    0.38
    久的
    0.37
    ান
    0.37
    巒
    0.37
    $)
    0.37
    POSITIVE LOGITS
    АН
    0.48
     Зо
    0.46
     самому
    0.46
    ANTI
    0.46
     навчання
    0.46
    OFF
    0.45
    ினான்
    0.45
    तत्
    0.45
     pallet
    0.45
    ވެ
    0.45
    Activations Density 0.000%

    No Known Activations