© 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. 22-GEMMASCOPE-RES-131K
    7. 34660
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

    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
     Türen
    -0.97
     ваших
    -0.90
    чения
    -0.88
    lawesi
    -0.88
    じ
    -0.85
    ALLA
    -0.84
    鳴
    -0.84
     外套
    -0.84
    чит
    -0.83
     höl
    -0.82
    POSITIVE LOGITS
     to
    1.29
     prét
    0.97
     and
    0.93
     but
    0.92
    Autores
    0.89
     mostrarán
    0.87
    にん
    0.85
    しまいます
    0.82
     mantienen
    0.82
    élection
    0.80
    Activations Density 0.000%

    No Known Activations