© 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. 10-GEMMASCOPE-RES-131K
    7. 84617
    Prev
    Next
    INDEX
    Explanations

    days months weeks of recognition

    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
     is
    -1.65
     if
    -1.56
     your
    -1.30
     and
    -1.27
     has
    -1.27
     entonces
    -1.18
     betere
    -1.15
     pouze
    -1.14
     illustratie
    -1.11
     jezelf
    -1.11
    POSITIVE LOGITS
    providedIn
    1.49
    プライベート
    1.40
    何故
    1.21
    インテリア
    1.20
    もとも
    1.20
     interesan
    1.20
    その他の
    1.19
    個人的には
    1.18
    カラオケ
    1.17
    HISTORIA
    1.16
    Activations Density 0.060%

    No Known Activations