© 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. 126801
    Prev
    Next
    INDEX
    Explanations

    attorney general, musical, wetlands, regret

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

    explicit sexual content and behavior

    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
     B
    0.45
     K
    0.45
     L
    0.44
     Extended
    0.44
     S
    0.42
     C
    0.42
     Thermo
    0.42
     Alpen
    0.42
     H
    0.41
     reference
    0.41
    POSITIVE LOGITS
    saraba
    0.51
    ǒu
    0.50
    CycleOffset
    0.49
    ត្ត
    0.49
    getPlayer
    0.49
    वानिव
    0.48
    ،
    0.48
    分之一
    0.47
    骂
    0.47
    aroos
    0.47
    Activations Density 0.001%

    No Known Activations