© 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. 79621
    Prev
    Next
    INDEX
    Explanations

    base64 keys and identifiers

    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
    犼
    -2.95
    趿
    -2.58
    ᠁
    -2.31
    骓
    -2.30
    踯
    -2.30
    ſſen
    -2.27
    ౭
    -2.14
     abd
    -2.13
    憷
    -2.13
     verschillende
    -2.11
    POSITIVE LOGITS
    '
    3.23
    5
    2.98
    A
    2.94
     or
    2.91
    0
    2.91
    It
    2.84
    This
    2.73
    (
    2.67
    /
    2.66
    I
    2.61
    Activations Density 0.030%

    No Known Activations