© 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. 98102
    Prev
    Next
    INDEX
    Explanations

    default

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

    default settings

    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
    真正
    0.52
    DLLEXPORT
    0.51
    真正的
    0.46
    ፃ
    0.44
     kesin
    0.43
    Paf
    0.41
    څ
    0.39
    有用
    0.38
    ጽ
    0.38
    걔
    0.38
    POSITIVE LOGITS
     default
    1.97
    默认
    1.86
     Default
    1.78
    default
    1.70
     defaults
    1.65
    デフォルト
    1.63
     defaulted
    1.60
     DEFAULT
    1.54
     Defaults
    1.53
     getDefault
    1.53
    Activations Density 0.165%

    No Known Activations