© 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. 193834
    Prev
    Next
    INDEX
    Explanations

    precedes following words

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

    information flows and sequences

    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
    වත්
    0.48
    नपुर
    0.47
    羌
    0.46
    崖
    0.45
     seperate
    0.45
     screenshot
    0.44
    p
    0.44
    TV
    0.43
     exon
    0.42
    ex
    0.40
    POSITIVE LOGITS
     ведь
    0.47
     อาท
    0.43
     وړاندوینه
    0.42
     gdyż
    0.42
     ಆರ್
    0.42
             
    0.41
     Ведь
    0.41
    齢
    0.40
     เช่น
    0.40
    žić
    0.40
    Activations Density 0.000%

    No Known Activations