© 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. 59512
    Prev
    Next
    INDEX
    Explanations

    designed for

    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
    𐄁
    -1.81
    高于
    -1.59
    seende
    -1.55
    believable
    -1.48
     You
    -1.48
     berücksich
    -1.45
     aktiven
    -1.45
     relacionado
    -1.45
     suspected
    -1.43
     evangé
    -1.42
    POSITIVE LOGITS
     and
    2.22
     with
    1.78
    These
    1.61
    With
    1.59
    Like
    1.56
    Either
    1.51
    Perhaps
    1.50
    Some
    1.49
    Much
    1.49
    Only
    1.44
    Activations Density 0.015%

    No Known Activations