© 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. 33691
    Prev
    Next
    INDEX
    Explanations

    news reports and investigations

    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
     for
    -1.93
    ׇ
    -1.61
     at
    -1.36
    !
    -1.33
     
    -1.33
     as
    -1.32
     there
    -1.31
     géographie
    -1.29
    :
    -1.27
     we
    -1.27
    POSITIVE LOGITS
    וּ
    2.08
    ַּ
    1.81
    ּוֹ
    1.63
    ֶּ
    1.52
    ᾿
    1.50
    Kleur
    1.49
    וֹ
    1.48
     تحقی
    1.40
     خریدار
    1.39
     început
    1.38
    Activations Density 0.060%

    No Known Activations