© 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. 45475
    Prev
    Next
    INDEX
    Explanations

    abbreviated units and names

    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
    Negative Logits
    u
    -2.91
    $
    -2.59
    "
    -2.38
    *
    -2.36
     К
    -2.31
    祈り
    -2.30
    敉
    -2.30
    ]
    -2.27
    of
    -2.17
     осіб
    -2.17
    POSITIVE LOGITS
    ſu
    3.19
    也會
    2.61
    噲
    2.59
    蟜
    2.44
     nimmer
    2.42
    侂
    2.38
    ſelf
    2.27
    </strong>
    2.25
     pauvreté
    2.23
    IBLIO
    2.20
    Activations Density 0.004%

    No Known Activations