© 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. 128860
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas

    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
     on
    -1.65
     not
    -1.61
     both
    -1.56
    ịch
    -1.41
     It
    -1.37
     while
    -1.36
     zis
    -1.33
     exercices
    -1.31
    емость
    -1.30
     all
    -1.27
    POSITIVE LOGITS
     ajudá
    1.60
    跟你
    1.33
     três
    1.28
     estadia
    1.27
     ayudan
    1.27
    סת
    1.26
    cillor
    1.23
    Autriche
    1.20
     fornecer
    1.20
     ensuing
    1.20
    Activations Density 0.009%

    No Known Activations