© 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. 10958
    Prev
    Next
    INDEX
    Explanations

    #food or #tattoo

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

    social media captions

    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
     PubMed
    0.41
     intravenously
    0.41
     unanswered
    0.40
     operand
    0.40
     Patient
    0.39
    \'{
    0.38
     introns
    0.38
     Proposition
    0.38
     dereg
    0.37
     Concentrations
    0.37
    POSITIVE LOGITS
    스타그램
    0.76
    instagood
    0.68
     #
    0.66
    Repost
    0.56
    ForThe
    0.55
    photography
    0.55
    ofinstagram
    0.54
    맛집
    0.54
     hashtag
    0.52
    bym
    0.50
    Activations Density 0.024%

    No Known Activations