© 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. 52
    Prev
    Next
    INDEX
    Explanations

    contains parts of names

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

    names and surnames

    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
     μεγαλύτε
    0.29
    鹜
    0.27
     infe
    0.27
     NaCl
    0.27
     πλη
    0.27
     πολ
    0.26
     בח
    0.26
    िसोदिया
    0.26
     угле
    0.26
     σημα
    0.26
    POSITIVE LOGITS
    an
    0.38
    ay
    0.34
    ik
    0.33
    ar
    0.32
    ama
    0.32
    al
    0.32
    u
    0.32
    ak
    0.31
    as
    0.31
    un
    0.31
    Activations Density 0.367%

    No Known Activations