© 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. 34-GEMMASCOPE-RES-131K
    7. 79445
    Prev
    Next
    INDEX
    Explanations

    total rehabilitation

    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
    Negative Logits
     kepentingan
    -0.79
    bau
    -0.74
    REME
    -0.73
    overall
    -0.73
    ін
    -0.72
     lamang
    -0.71
    стный
    -0.71
    Bau
    -0.71
    📲
    -0.71
     Jury
    -0.70
    POSITIVE LOGITS
     ),
    0.84
    oarece
    0.83
     zů
    0.82
    ])+
    0.82
    .),
    0.81
    "]);
    0.80
    ?>">
    0.79
    〟
    0.79
    一个人
    0.78
     allarg
    0.78
    Activations Density 0.001%

    No Known Activations