© 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. 223527
    Prev
    Next
    INDEX
    Explanations

    family relationships

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

    between libraries

    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
    argas
    0.48
    Vlad
    0.47
    ర్రీ
    0.44
    ዬ
    0.44
    Toe
    0.43
     성능
    0.43
    бры
    0.42
    酞
    0.42
    Ani
    0.42
    iria
    0.42
    POSITIVE LOGITS
     grandson
    0.55
     haus
    0.52
     suami
    0.49
     autore
    0.49
     sem
    0.49
     euch
    0.48
     nephew
    0.48
     sun
    0.48
     italiana
    0.47
     grandsons
    0.47
    Activations Density 0.022%

    No Known Activations