© 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. 61777
    Prev
    Next
    INDEX
    Explanations

    packaging details

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

    minimize symbol clashes

    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
     बनाना
    0.45
    を使って
    0.45
    を使用して
    0.45
     prudence
    0.43
    を使
    0.42
     색
    0.42
    が登場
    0.41
     기
    0.41
    를
    0.41
    โบ
    0.41
    POSITIVE LOGITS
     પરિવાર
    0.43
     ενη
    0.40
     Configur
    0.39
    该
    0.39
    腚
    0.39
     δύ
    0.38
    jav
    0.38
    亲
    0.38
     त्यात
    0.38
     भ्र
    0.38
    Activations Density 0.000%

    No Known Activations