© 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. 101865
    Prev
    Next
    INDEX
    Explanations

    lunch followed by at or cruise

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

    following certain tokens

    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
    ഥ
    0.50
    Wt
    0.46
     interpol
    0.45
     všetky
    0.45
     exprim
    0.44
    Ej
    0.43
     Biss
    0.43
    Sis
    0.43
    id
    0.43
     Pública
    0.43
    POSITIVE LOGITS
    counterx
    0.48
    詼
    0.47
    看的
    0.46
    詳細は
    0.46
     skul
    0.45
    )【
    0.44
     横
    0.44
    ݢ
    0.44
    産の
    0.43
    shield
    0.43
    Activations Density 0.000%

    No Known Activations