© 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. 174478
    Prev
    Next
    INDEX
    Explanations

    business, markets, and branding

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

    letting go

    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
    rían
    0.52
    tooltip
    0.51
     ஒரே
    0.50
    dyž
    0.47
    except
    0.46
    ↵↵
    0.46
    adobe
    0.45
    reject
    0.45
    flo
    0.45
     природ
    0.45
    POSITIVE LOGITS
    জি
    0.57
     GOLD
    0.49
    <unused303>
    0.48
     ODDS
    0.45
     plantings
    0.44
     REGULATIONS
    0.44
    Punch
    0.44
     dấu
    0.43
     PUN
    0.43
    ㅣ
    0.43
    Activations Density 0.001%

    No Known Activations