© 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. 58277
    Prev
    Next
    INDEX
    Explanations

    quick deployment

    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
     and
    -1.88
    }
    -1.48
    })-
    -1.30
     seleccionamos
    -1.30
    ньому
    -1.22
     tempera
    -1.20
    OMETRY
    -1.20
    </h2>
    -1.20
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.19
    patra
    -1.18
    POSITIVE LOGITS
     convain
    1.29
     one
    1.17
     razem
    1.14
     other
    1.14
    が無い
    1.12
     nœ
    1.12
    TextWatcher
    1.11
    TextBoxColumn
    1.09
    łac
    1.09
     that
    1.07
    Activations Density 0.100%

    No Known Activations