© 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. 152279
    Prev
    Next
    INDEX
    Explanations

    names and dates

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

    Ugh, annoyed reluctance

    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
    ﮨ
    0.53
    ایک
    0.51
    دی
    0.49
     biasing
    0.49
    ળ
    0.47
    ત
    0.46
    ଛ
    0.46
     یک
    0.46
    زی
    0.46
     países
    0.46
    POSITIVE LOGITS
     ICP
    0.49
     Frederick
    0.48
     Cornelia
    0.47
     Henrietta
    0.46
     Vermeer
    0.46
     Reihen
    0.45
     Dole
    0.44
     IPL
    0.43
     Raleigh
    0.43
     Edwin
    0.43
    Activations Density 0.001%

    No Known Activations