© 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. 13451
    Prev
    Next
    INDEX
    Explanations

    Kavanaugh, Walls,opolis, Jeezy

    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
    ...
    -1.44
    ’
    -1.32
    --
    -1.27
    </td>
    -1.21
    几分
    -1.19
    (&
    -1.18
    了几
    -1.16
    '
    -1.16
    鞄
    -1.13
      
    -1.10
    POSITIVE LOGITS
     a
    1.55
    nyata
    1.52
    ğına
    1.51
     such
    1.36
     our
    1.35
    饧
    1.34
     particularly
    1.34
     acogedor
    1.32
    legging
    1.31
    "])
    1.31
    Activations Density 0.102%

    No Known Activations