© 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. 57177
    Prev
    Next
    INDEX
    Explanations

    values, RGB, progress

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

    price indication ($, $$, $$$)

    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
    il
    0.54
    fi
    0.47
     частью
    0.47
     Ipswich
    0.44
    1
    0.44
    led
    0.43
     Finch
    0.41
     समृद्धि
    0.41
     FPS
    0.41
     benchmarks
    0.40
    POSITIVE LOGITS
    오는
    0.54
    ده
    0.51
    פר
    0.50
    ้ง
    0.49
    ரா
    0.48
    מר
    0.47
    يكون
    0.47
     misura
    0.47
     musul
    0.46
    ᕐ
    0.46
    Activations Density 0.000%

    No Known Activations