© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21979
    Prev
    Next
    INDEX
    Explanations

    creating mental images

    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
     TÉCNICA
    -1.52
    Informazioni
    -1.45
    闈
    -1.45
    一愣
    -1.42
     músicos
    -1.42
     paio
    -1.41
    𓈒
    -1.41
    VIATIONS
    -1.39
     spagno
    -1.38
    終於
    -1.37
    POSITIVE LOGITS
    ut
    1.63
     __________
    1.55
    ak
    1.53
    </i>
    1.49
    </strong>
    1.46
    達が
    1.44
    >=</
    1.44
     visualizing
    1.42
    __()
    1.42
    er
    1.40
    Activations Density 0.028%

    No Known Activations