© 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. 10-GEMMASCOPE-RES-131K
    7. 123539
    Prev
    Next
    INDEX
    Explanations

    INFO followed by colon or underscore

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "INFO" in all-caps, typically in technical contexts like logging statements, code constants, or formal document identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    A
    -4.03
    What
    -3.94
    1
    -3.66
    At
    -3.52
    For
    -3.42
    When
    -3.36
    How
    -3.31
    In
    -3.28
    An
    -3.22
    On
    -3.17
    POSITIVE LOGITS
    .
    3.05
    榈
    2.91
    埽
    2.67
    踽
    2.47
    béco
    2.42
    屙
    2.41
    鮓
    2.41
    かもし
    2.36
    錚
    2.34
    すすめ
    2.33
    Activations Density 0.006%

    No Known Activations