© 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. 35735
    Prev
    Next
    INDEX
    Explanations

    car parts or features

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

    not just

    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
     inferiores
    0.57
     scala
    0.46
     abund
    0.46
     facil
    0.45
    還元
    0.45
    鍔
    0.45
    是對
    0.45
     inferior
    0.44
    드
    0.44
     scare
    0.44
    POSITIVE LOGITS
    fieldName
    0.46
    pN
    0.45
    moduleId
    0.45
    ashmir
    0.44
    Whole
    0.43
    ({},
    0.43
    SourceName
    0.43
    arguments
    0.43
    CoO
    0.43
    topnav
    0.43
    Activations Density 0.000%

    No Known Activations