© 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. 39990
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements

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

    Fermi level

    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
     других
    0.47
    шни
    0.47
    搾
    0.47
     Israël
    0.46
    ()?>
    0.45
    Israel
    0.45
    舞
    0.44
     Израи
    0.44
    薊
    0.44
     کمپنیوں
    0.44
    POSITIVE LOGITS
     drill
    0.57
     skimage
    0.56
     freestyle
    0.54
    dehyde
    0.52
    biti
    0.52
     stoneware
    0.52
     photosynthesis
    0.51
     gain
    0.50
     reposition
    0.50
     die
    0.49
    Activations Density 0.000%

    No Known Activations