© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57932
    Prev
    Next
    INDEX
    Explanations

    asking to name specific items

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

    name and identify aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resolve
    0.45
     构建
    0.44
     calculate
    0.43
     Prepare
    0.41
     نع
    0.41
     นํา
    0.41
     ユ
    0.41
     计算
    0.40
     R
    0.40
     Calculate
    0.40
    POSITIVE LOGITS
    igheter
    0.46
    慈善
    0.46
    igheten
    0.45
    portál
    0.45
    Ссы
    0.44
    Це
    0.43
    Ბ
    0.43
    That
    0.42
    तलब
    0.42
    妷
    0.42
    Activations Density 0.002%

    No Known Activations