© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43564
    Prev
    Next
    INDEX
    Explanations

    in action

    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
     that
    -1.69
     likely
    -1.65
     '/':
    -1.50
     schim
    -1.49
    the
    -1.43
    ائج
    -1.40
    ‘
    -1.40
     případ
    -1.37
     rijk
    -1.36
    S
    -1.36
    POSITIVE LOGITS
    olução
    1.48
    ípios
    1.48
    }$.
    1.48
     likes
    1.47
    )$.
    1.46
     acknowledges
    1.45
     ;
    1.44
    Explicación
    1.43
     giebt
    1.41
     :
    1.41
    Activations Density 0.010%

    No Known Activations