© 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. 182393
    Prev
    Next
    INDEX
    Explanations

    reading or writing

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

    specific applications or services

    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
    क्रम
    0.50
    借り
    0.49
    ण
    0.48
    인이
    0.48
     dịp
    0.48
    몇
    0.48
    क्रामक
    0.47
    км
    0.47
     discíp
    0.46
    ╅
    0.46
    POSITIVE LOGITS
    ↵↵
    0.45
    ReadAll
    0.42
    ine
    0.42
     absorbance
    0.41
    sel
    0.41
     mindfulness
    0.39
     ;
    0.39
    IV
    0.38
     radiography
    0.38
    Del
    0.38
    Activations Density 0.000%

    No Known Activations