© 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. 22-GEMMASCOPE-RES-131K
    7. 66396
    Prev
    Next
    INDEX
    Explanations

    media titles or franchises

    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
     новых
    -1.66
     данной
    -1.47
     stiefel
    -1.45
     новый
    -1.45
     revamped
    -1.43
    蕺
    -1.42
     adesi
    -1.42
     adesivo
    -1.41
     広場
    -1.41
    フック
    -1.41
    POSITIVE LOGITS
     on
    1.88
     From
    1.70
     to
    1.68
     There
    1.67
     When
    1.64
     With
    1.62
     While
    1.60
     what
    1.58
     at
    1.53
     as
    1.51
    Activations Density 0.020%

    No Known Activations