© 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. 14710
    Prev
    Next
    INDEX
    Explanations

    python code context

    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
     tycker
    0.21
     indicates
    0.21
     দেখতে
    0.20
     petitioner
    0.20
     jTextField
    0.20
     progenitor
    0.20
     বুঝতে
    0.20
     "${
    0.20
    ূল্য
    0.20
     interviewee
    0.20
    POSITIVE LOGITS
    スポーツ
    0.25
     स्पोर्ट्स
    0.22
    コンビニ
    0.22
    ཛ
    0.22
    ESPN
    0.22
    BIB
    0.21
    トレーニング
    0.21
    منابع
    0.21
    муж
    0.21
    Tune
    0.21
    Activations Density 0.000%

    No Known Activations