© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118097
    Prev
    Next
    INDEX
    Explanations

    dash and stroke styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ผ่าน
    -0.80
    setFirstName
    -0.75
     cadenas
    -0.73
     downvote
    -0.73
    urare
    -0.71
    హ
    -0.71
    œ
    -0.71
    (++
    -0.71
    事務所
    -0.71
     strong
    -0.71
    POSITIVE LOGITS
    dash
    1.21
     dash
    1.17
     Dash
    1.13
    Dash
    0.99
     mit
    0.98
    DASH
    0.98
     Das
    0.97
     capping
    0.93
     cap
    0.91
     dashing
    0.91
    Activations Density 0.015%

    No Known Activations