© 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. 22-GEMMASCOPE-RES-131K
    7. 72496
    Prev
    Next
    INDEX
    Explanations

    awards and ceremonies

    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_22/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
     recently
    -1.27
    を考える
    -1.17
     can
    -1.09
     Deixe
    -1.09
     participaron
    -1.09
     often
    -1.08
     acudi
    -1.07
     Qualquer
    -1.05
    ündig
    -1.05
    pośred
    -1.02
    POSITIVE LOGITS
     the
    1.43
     firft
    1.20
    nesse
    1.19
    biter
    1.16
    🏈
    1.15
    цыі
    1.13
    ourses
    1.11
     departement
    1.10
    ???:
    1.10
     minn
    1.10
    Activations Density 0.059%

    No Known Activations