© 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. 34013
    Prev
    Next
    INDEX
    Explanations

    English code keywords

    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
     their
    -1.26
     always
    -1.23
     like
    -1.18
     and
    -1.12
     its
    -1.09
    $.}
    -1.09
     If
    -1.07
    来週
    -1.06
    んでしょう
    -1.06
     that
    -1.05
    POSITIVE LOGITS
    これも
    1.15
    を
    1.14
    atized
    1.07
    もあり
    1.06
    atization
    1.04
    alised
    1.02
    ۔
    1.02
    뭄
    1.01
    姿
    1.00
    šče
    1.00
    Activations Density 0.006%

    No Known Activations