© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59247
    Prev
    Next
    INDEX
    Explanations

    intr / intra- / Rt

    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
    惲
    -2.78
    蕺
    -2.75
    曩
    -2.63
    齶
    -2.59
    烺
    -2.44
    ्ञ
    -2.39
    縷
    -2.39
    弖
    -2.36
    霂
    -2.34
    侭
    -2.34
    POSITIVE LOGITS
    '
    3.19
    3
    2.83
    2
    2.56
    Is
    2.53
     "
    2.48
    <strong>
    2.47
    4
    2.47
    and
    2.45
    ING
    2.44
    d
    2.44
    Activations Density 0.008%

    No Known Activations