© 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. 8153
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
     to
    -1.26
    atief
    -1.20
     oba
    -1.19
     Să
    -1.16
    );
    -1.12
     INFORMACIÓN
    -1.10
    کنندگان
    -1.09
     Although
    -1.07
     المختلفة
    -1.06
    atieve
    -1.05
    POSITIVE LOGITS
    ↵
    1.23
      
    1.22
    BCM
    1.18
     turista
    1.12
     Forse
    1.11
    贫
    1.10
     principalmente
    1.09
    might
    1.09
    since
    1.08
    merk
    1.08
    Activations Density 0.006%

    No Known Activations