© 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. 113326
    Prev
    Next
    INDEX
    Explanations

    words starting with PH

    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
    $
    -3.14
    Not
    -3.11
    Like
    -3.08
    Since
    -3.06
    Perhaps
    -3.05
    In
    -2.98
    Only
    -2.97
    From
    -2.95
    For
    -2.94
     However
    -2.92
    POSITIVE LOGITS
    ୬
    3.00
    缡
    2.86
    𝄆
    2.78
    𖤍
    2.75
    ఽ
    2.75
    𐬹
    2.69
     zijn
    2.61
    閙
    2.59
    萏
    2.50
    鸲
    2.48
    Activations Density 0.005%

    No Known Activations