© 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. 86616
    Prev
    Next
    INDEX
    Explanations

    free entry

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

    essentials

    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
    され
    0.58
    金額
    0.56
     지급
    0.56
    込ま
    0.53
    鉅
    0.50
    摯
    0.49
    財
    0.48
    價
    0.48
    誠
    0.47
    賃
    0.47
    POSITIVE LOGITS
    an
    0.58
    shape
    0.51
     drie
    0.51
    sparse
    0.49
    anaconda
    0.48
    onter
    0.47
     probleem
    0.47
    formatics
    0.47
     resveratrol
    0.47
    onen
    0.46
    Activations Density 0.000%

    No Known Activations