© 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. 25532
    Prev
    Next
    INDEX
    Explanations

    personal statements and actions

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

    self and relationships

    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
    Ciudad
    0.38
     собі
    0.36
     న
    0.36
    צא
    0.36
    公寓
    0.36
    价
    0.36
    Miami
    0.35
    Squ
    0.34
    辭
    0.34
     ನೆ
    0.34
    POSITIVE LOGITS
     email
    0.41
     epidemiology
    0.38
    ರೀಕ್ಷ
    0.38
     کوډ
    0.38
    uteurs
    0.37
     Strauss
    0.37
    畦
    0.37
     crochet
    0.37
    に必要な
    0.37
     Lily
    0.36
    Activations Density 0.082%

    No Known Activations