© 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. 136460
    Prev
    Next
    INDEX
    Explanations

    prove and proving

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

    understand prompts

    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
     simplifié
    0.47
     zusätz
    0.47
    }\
    0.47
    }&=
    0.46
     Mosby
    0.46
     تاريخ
    0.45
     gostar
    0.45
     अंश
    0.44
     政府
    0.44
     Agama
    0.44
    POSITIVE LOGITS
    species
    0.54
    prove
    0.53
    iapkan
    0.51
    opportunities
    0.51
    i
    0.47
     species
    0.45
    пом
    0.44
    Romania
    0.44
    testimon
    0.44
    proving
    0.44
    Activations Density 0.000%

    No Known Activations