© 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. 218970
    Prev
    Next
    INDEX
    Explanations

    rentals allowed

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

    humanize

    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
     впоследствии
    0.49
     REGIUNI
    0.46
     목적
    0.46
     lawfully
    0.45
     அளித்த
    0.45
    関
    0.44
    筚
    0.44
    ář
    0.44
     lawful
    0.44
    财务
    0.44
    POSITIVE LOGITS
     sele
    0.45
    snapshots
    0.45
     on
    0.44
    az
    0.43
    strs
    0.43
    poi
    0.42
     যান
    0.42
     oi
    0.42
    nouns
    0.41
    s
    0.41
    Activations Density 0.000%

    No Known Activations