© 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. 74319
    Prev
    Next
    INDEX
    Explanations

    horizontal at

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

    specific formatting and punctuation

    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
     (
    0.47
     where
    0.46
     I
    0.45
      
    0.44
    where
    0.44
     production
    0.44
     but
    0.42
     yet
    0.42
     “
    0.41
    ↵
    0.41
    POSITIVE LOGITS
     અધિકારી
    0.49
     बालकनियां
    0.46
     વિભાગ
    0.46
     escritorio
    0.46
    MathMarks
    0.45
    ビック
    0.45
     മാലി
    0.45
    ).(
    0.45
     سینٹی
    0.45
    ਡ
    0.44
    Activations Density 0.000%

    No Known Activations