© 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. 42386
    Prev
    Next
    INDEX
    Explanations

    code blocks and structure definition

    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_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
    \
    -3.52
    s
    -3.16
    8
    -2.80
     .
    -2.58
    6
    -2.53
    本当に
    -2.52
    "
    -2.48
    ２
    -2.48
    :
    -2.42
    -
    -2.38
    POSITIVE LOGITS
    zelfde
    2.81
    ’,
    2.80
     commensurate
    2.78
    ”—
    2.72
    亟
    2.59
    >
    2.58
     fundamentos
    2.56
    苾
    2.56
     groter
    2.52
    er
    2.50
    Activations Density 0.002%

    No Known Activations