© 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. 133975
    Prev
    Next
    INDEX
    Explanations

    referring to self or others

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

    accessing specific services or concerns

    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
    <0x80>
    0.46
    <0x84>
    0.44
    😕
    0.44
     откуда
    0.43
     инсу
    0.43
     помо
    0.43
    iyê
    0.43
     ү
    0.42
    recieve
    0.42
     தெரிவித்தனர்
    0.42
    POSITIVE LOGITS
    大规模
    0.46
     verk
    0.44
     comod
    0.44
     alqu
    0.44
     removal
    0.43
     problemat
    0.43
    膦
    0.43
     commod
    0.41
     dada
    0.41
    مال
    0.41
    Activations Density 0.000%

    No Known Activations