© 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. 183484
    Prev
    Next
    INDEX
    Explanations

    proper nouns

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

    Noir, Rates, Empathy

    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
     UIText
    0.54
    𝗗
    0.53
     মেসি
    0.52
     മതി
    0.52
    缟
    0.52
    マーク
    0.52
     значений
    0.51
    ׄ
    0.51
    𝗇
    0.50
    َاب
    0.50
    POSITIVE LOGITS
    iaz
    0.55
     Ge
    0.54
    fra
    0.54
    }\
    0.50
    Ig
    0.49
     Tro
    0.49
     Christians
    0.48
     Sir
    0.48
    Ge
    0.48
    con
    0.47
    Activations Density 0.000%

    No Known Activations