© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43589
    Prev
    Next
    INDEX
    Explanations

    Diablo III / creativecommons / snowball sampling

    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_10/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
    嵛
    -2.48
    ⡯
    -2.28
    癀
    -2.28
    𖣘
    -2.14
     seier
    -2.14
     adoro
    -2.13
    </h5>
    -2.09
    ↵
    -2.09
    ୈ
    -2.03
     bukanlah
    -1.96
    POSITIVE LOGITS
    л
    2.38
     We
    2.14
    $,
    2.05
     ilusión
    2.03
    '
    1.98
     he
    1.96
     zwanzig
    1.94
    疳
    1.92
    rts
    1.84
    ized
    1.82
    Activations Density 0.011%

    No Known Activations