© 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. 64957
    Prev
    Next
    INDEX
    Explanations

    temperature level

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

    silent motion, molecular vibration

    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
    gados
    0.53
    ances
    0.47
    ifold
    0.46
    ifer
    0.44
    ityanath
    0.44
     sunset
    0.43
    arantine
    0.43
    <0x9A>
    0.42
    ائدة
    0.42
    će
    0.42
    POSITIVE LOGITS
    AST
    0.52
    ERA
    0.50
    SF
    0.48
    Selen
    0.47
    JI
    0.47
     Atti
    0.46
     Mö
    0.46
     Strang
    0.46
    ASE
    0.46
    AAAAAAAA
    0.46
    Activations Density 0.000%

    No Known Activations