© 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. 158264
    Prev
    Next
    INDEX
    Explanations

    law information achieve ages skills many nation

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

    identifying specific entities and their attributes

    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
    وص
    0.46
    ப்பில்
    0.45
     تیم
    0.45
     již
    0.44
    ദ്ധതി
    0.44
    ჟ
    0.42
    خراج
    0.42
    هاز
    0.42
    好
    0.42
    ösungen
    0.41
    POSITIVE LOGITS
    mood
    0.48
    fires
    0.45
     mood
    0.44
     ск
    0.44
    dark
    0.41
     ち
    0.41
    äche
    0.41
     flirt
    0.41
    daw
    0.41
     texture
    0.41
    Activations Density 0.001%

    No Known Activations