© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72002
    Prev
    Next
    INDEX
    Explanations

    ObjectMapper, gutted, Sandman, blackened

    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
    “
    -2.97
    痦
    -2.70
     تستخدم
    -2.64
    американ
    -2.63
     Когда
    -2.56
    沺
    -2.56
    玊
    -2.53
    珦
    -2.48
    sukienka
    -2.45
    婓
    -2.39
    POSITIVE LOGITS
    ]
    3.02
     盗
    2.36
    )-
    2.31
     was
    2.16
     then
    2.14
    ="
    2.13
     podem
    2.09
     ומ
    2.05
    ){
    2.05
    </sup>
    2.05
    Activations Density 0.004%

    No Known Activations