© 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. 158466
    Prev
    Next
    INDEX
    Explanations

    most popular superlative

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

    contrasting or qualifying statements

    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
    <end_of_turn>
    0.48
    histo
    0.45
    िटीज
    0.45
    াস্থ্য
    0.44
     resistenza
    0.44
    itsch
    0.43
     ricerca
    0.42
    chond
    0.42
    তরাং
    0.42
    icyclo
    0.42
    POSITIVE LOGITS
     "`
    0.49
     req
    0.47
     app
    0.46
     भे
    0.46
     /
    0.46
     "(
    0.45
     a
    0.45
     "
    0.45
     corroborate
    0.45
     ")
    0.43
    Activations Density 0.000%

    No Known Activations