© 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. 159537
    Prev
    Next
    INDEX
    Explanations

    understand, recommends, venue

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

    understanding confirmation

    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
    록
    0.46
     цвета
    0.46
     ווע
    0.45
    사
    0.44
     assh
    0.42
    过后
    0.42
    테
    0.42
    クレ
    0.42
     אפ
    0.41
     ავ
    0.41
    POSITIVE LOGITS
    р
    0.50
    umur
    0.48
    رود
    0.47
    ileen
    0.46
    ermott
    0.46
    ι
    0.46
    ргани
    0.45
    royd
    0.44
    燃
    0.44
     photospheric
    0.44
    Activations Density 0.000%

    No Known Activations