© 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. 73066
    Prev
    Next
    INDEX
    Explanations

    software libraries and frameworks

    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
     While
    -2.89
     If
    -2.55
    providedIn
    -2.30
     impressive
    -2.22
     Though
    -2.22
     There
    -2.17
     Even
    -2.16
     from
    -2.14
     Although
    -2.14
     has
    -2.09
    POSITIVE LOGITS
    ↵
    2.59
    擼
    2.48
    ふわふわ
    2.41
    茈
    2.31
     "*
    2.31
     captivating
    2.30
    (“
    2.27
     delightfully
    2.27
    鶿
    2.23
     masterful
    2.22
    Activations Density 0.002%

    No Known Activations