© 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. 66212
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@R] or [@CR]

    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
     аккура
    -1.70
     baterie
    -1.63
    嗚
    -1.59
    ＄
    -1.58
    鱷
    -1.57
    熜
    -1.56
    ֢
    -1.56
    länger
    -1.56
     Berlín
    -1.55
     hırka
    -1.54
    POSITIVE LOGITS
    e
    2.50
    </strong>
    2.45
    se
    1.97
    g
    1.93
     is
    1.91
    n
    1.84
    f
    1.80
    だが
    1.75
    h
    1.72
    u
    1.72
    Activations Density 0.000%

    No Known Activations