© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71106
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    L
    -1.61
    N
    -1.34
     aka
    -1.24
    A
    -1.23
    ing
    -1.21
    ;
    -1.20
    :
    -1.20
    のでしょう
    -1.20
     utaf
    -1.19
     our
    -1.18
    POSITIVE LOGITS
     могат
    1.38
    artment
    1.34
    DAFTAR
    1.30
     onPostExecute
    1.30
     dilakukan
    1.27
    fordshire
    1.26
    Hü
    1.25
    Punkt
    1.24
     poderão
    1.23
    釓
    1.23
    Activations Density 0.048%

    No Known Activations