© 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. 32998
    Prev
    Next
    INDEX
    Explanations

    received, kept, made, without

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

    lists of items or aspects

    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
     Thomas
    0.59
    0.54
     Ве
    0.54
    ↵↵
    0.54
     Lillian
    0.52
     Lorenzo
    0.51
     Auditorium
    0.51
     José
    0.50
     that
    0.50
     Harry
    0.50
    POSITIVE LOGITS
     уйнарга
    0.53
    ecology
    0.50
    😭
    0.45
    😥
    0.44
     efficacy
    0.44
     уйный
    0.44
    ষণের
    0.44
    этому
    0.43
    廨
    0.43
     detergent
    0.43
    Activations Density 0.000%

    No Known Activations