© 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. 67070
    Prev
    Next
    INDEX
    Explanations

    Al followed by nA

    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
    ógrafo
    -0.93
    доступ
    -0.88
     植物
    -0.88
    揺
    -0.85
    краси
    -0.84
    welling
    -0.84
    inderung
    -0.83
     betont
    -0.83
     sisält
    -0.82
    ៗ
    -0.82
    POSITIVE LOGITS
    less
    0.91
     effect
    0.87
     null
    0.84
     early
    0.81
     intervention
    0.78
     nil
    0.78
     enabled
    0.77
     Lern
    0.77
     effects
    0.76
    madan
    0.76
    Activations Density 0.191%

    No Known Activations