© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12346
    Prev
    Next
    INDEX
    Explanations

    describing a problem

    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
    錞
    -3.34
    떳
    -3.06
    苳
    -3.03
    猡
    -2.53
    sandalia
    -2.52
    螃
    -2.50
    ágenes
    -2.48
    痿
    -2.47
    鲧
    -2.44
     druck
    -2.42
    POSITIVE LOGITS
     Also
    3.22
    .
    3.16
     However
    3.11
     Only
    2.64
     Roughly
    2.59
    ”,
    2.52
    人を
    2.48
    м
    2.45
    al
    2.44
     That
    2.42
    Activations Density 0.005%

    No Known Activations