© 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. 224762
    Prev
    Next
    INDEX
    Explanations

    date and official stamps

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

    timestamp default current_timestamp

    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
    纤
    0.58
    ｉ
    0.52
     STATIC
    0.48
     হওয়ায়
    0.48
     ሳ
    0.47
     অভিনেত্র
    0.46
     מו
    0.46
     হওয়ায়
    0.46
    孙
    0.46
    烧
    0.46
    POSITIVE LOGITS
    ambuk
    0.55
     vow
    0.43
     Pemerintah
    0.43
     inscrito
    0.42
     lawful
    0.42
    UMNS
    0.42
     inscrição
    0.42
     bipartisan
    0.41
     condemned
    0.41
     diplomat
    0.40
    Activations Density 0.000%

    No Known Activations