© 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. 172974
    Prev
    Next
    INDEX
    Explanations

    making decisions and taking actions

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

    most common or concise

    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
    V
    0.54
    Sp
    0.48
    ED
    0.46
     V
    0.44
    Sharing
    0.43
    OR
    0.43
    iania
    0.43
    stress
    0.42
    ia
    0.41
     tirelessly
    0.41
    POSITIVE LOGITS
     チ
    0.51
     желу
    0.51
    ごろ
    0.50
     aproape
    0.48
     indigestion
    0.47
     sağlı
    0.46
     แน
    0.45
     ያለው
    0.45
     omissions
    0.45
     あっ
    0.45
    Activations Density 0.001%

    No Known Activations