© 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. 203879
    Prev
    Next
    INDEX
    Explanations

    relative clauses

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

    structure and organization

    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
     FGD
    0.49
     assailant
    0.47
    aggressive
    0.46
     باس
    0.46
     MSU
    0.45
     @"
    0.45
    PropertyGroup
    0.45
    weight
    0.44
     Ms
    0.44
    atable
    0.44
    POSITIVE LOGITS
    즈
    0.52
    턴
    0.47
    Differences
    0.46
     différences
    0.45
    书
    0.45
    서트
    0.44
    正
    0.44
    녠
    0.44
    绳
    0.43
     voltak
    0.43
    Activations Density 0.001%

    No Known Activations