© 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. 56035
    Prev
    Next
    INDEX
    Explanations

    organizations and their actions

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

    technical identifiers and actions

    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
    ్య
    0.46
    ు
    0.40
     వ్యక్
    0.38
    હા
    0.38
     물론
    0.38
    šky
    0.38
    ळून
    0.37
    ˁ
    0.37
    amaran
    0.37
     ตาม
    0.36
    POSITIVE LOGITS
     recommends
    0.64
     strives
    0.62
     provides
    0.61
     accepts
    0.61
     recognizes
    0.59
     welcomes
    0.59
     gives
    0.57
     considers
    0.57
     spends
    0.55
     owns
    0.55
    Activations Density 0.047%

    No Known Activations