© 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. 22-GEMMASCOPE-RES-131K
    7. 16176
    Prev
    Next
    INDEX
    Explanations

    is absolutely

    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
     dagens
    -1.17
     uusi
    -1.13
    ांकि
    -1.10
     cruelly
    -1.09
    我现在
    -1.06
    ();
    -1.06
    如果不
    -1.05
     });
    -1.05
    se
    -1.05
    往往
    -1.04
    POSITIVE LOGITS
     like
    1.23
    婓
    1.17
     oslo
    1.13
    caucasian
    1.11
    淠
    1.10
     also
    1.09
     only
    1.09
    langkah
    1.06
    kenzo
    1.05
     kabát
    1.05
    Activations Density 0.135%

    No Known Activations