© 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. 121967
    Prev
    Next
    INDEX
    Explanations

    academic requirements

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

    breaking down into sections

    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
     branchNode
    0.48
     summand
    0.47
     सर्वेक्षण
    0.45
     kosong
    0.44
     वसूली
    0.44
     zove
    0.44
    TreeClassifier
    0.44
     ត
    0.43
     afectadas
    0.43
     afectada
    0.42
    POSITIVE LOGITS
    CE
    0.45
    guests
    0.44
    每个人
    0.42
    RE
    0.42
    用户的
    0.42
    ्स
    0.41
    креп
    0.41
    s
    0.41
    但在
    0.41
    ᒧ
    0.40
    Activations Density 0.000%

    No Known Activations