© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75245
    Prev
    Next
    INDEX
    Explanations

    i am using

    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
     I
    -1.88
     Its
    -1.73
    ,.
    -1.64
    -.
    -1.49
    :.
    -1.48
     But
    -1.45
    焌
    -1.45
    を使った
    -1.43
     $
    -1.42
    怎么回事
    -1.41
    POSITIVE LOGITS
    鬭
    1.38
     voeten
    1.33
    няют
    1.30
    although
    1.29
     wensen
    1.28
     there
    1.28
     グループ
    1.28
    ائے
    1.27
    iettivo
    1.27
     kenaikan
    1.26
    Activations Density 0.095%

    No Known Activations