© 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. 22-GEMMASCOPE-RES-131K
    7. 39667
    Prev
    Next
    INDEX
    Explanations

    elseelseelseelseelse)-bySummaryCMedia

    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
    vereign
    -0.91
     CYTHON
    -0.88
    atorium
    -0.85
    ternut
    -0.85
    termilk
    -0.84
    znál
    -0.83
     delighted
    -0.82
    DrawLine
    -0.82
    mobileqq
    -0.81
    ormais
    -0.80
    POSITIVE LOGITS
     equivalents
    1.01
     toimi
    0.84
     equivalent
    0.82
     FIR
    0.81
    obbies
    0.80
    cosal
    0.80
    OWSKI
    0.79
    действие
    0.78
     older
    0.77
     umana
    0.77
    Activations Density 0.011%

    No Known Activations