© 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. 177545
    Prev
    Next
    INDEX
    Explanations

    design free proper

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

    handling common basic electrical

    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
     רו
    0.63
     ז
    0.57
    F
    0.53
    房价
    0.52
     ದೊ
    0.51
     DENUMIRE
    0.49
    G
    0.49
     יו
    0.49
     "',
    0.48
     انتظار
    0.48
    POSITIVE LOGITS
    ing
    0.54
    ｙ
    0.50
    ed
    0.48
    edge
    0.47
    ystyrene
    0.46
    edges
    0.45
    ел
    0.44
    en
    0.44
    yt
    0.44
    ழுது
    0.43
    Activations Density 0.000%

    No Known Activations