© 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. 197169
    Prev
    Next
    INDEX
    Explanations

    conditions or states

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

    keep secure

    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
    クーポン
    0.52
     صدیق
    0.51
     שמ
    0.48
    ẋ
    0.47
    鍖
    0.46
     توهان
    0.45
     ני
    0.44
     Muay
    0.44
    ︱
    0.44
     کہنے
    0.43
    POSITIVE LOGITS
     tragic
    0.43
     understandably
    0.41
     perilous
    0.41
    contexts
    0.39
    했지만
    0.39
     context
    0.38
    context
    0.38
     defensively
    0.37
    危険
    0.37
     geology
    0.37
    Activations Density 0.000%

    No Known Activations