© 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. 45596
    Prev
    Next
    INDEX
    Explanations

    locations with street or place names

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

    AI models and named entities

    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
    的时候
    0.47
     ২০১১
    0.47
     WIFI
    0.46
    旁边
    0.44
     =)
    0.44
     Pubmed
    0.43
    ொழுது
    0.43
     까지
    0.42
     이용하여
    0.41
     (?)
    0.40
    POSITIVE LOGITS
    reported
    0.44
    <unused1100>
    0.40
    wali
    0.40
    committed
    0.40
     따르면
    0.40
    told
    0.40
     toutefois
    0.39
    <unused1068>
    0.39
    battle
    0.39
    ruled
    0.39
    Activations Density 0.031%

    No Known Activations