© 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. 27446
    Prev
    Next
    INDEX
    Explanations

    transaction; it

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

    punctuation followed by it

    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
     straightforward
    0.54
     ankaŭ
    0.47
     solely
    0.42
     भी
    0.42
    也要
    0.42
    的双
    0.42
    ཇ
    0.42
     بھی
    0.41
     spotlight
    0.41
     देखील
    0.41
    POSITIVE LOGITS
    امله
    0.49
    spirit
    0.47
    become
    0.47
    -|
    0.44
    into
    0.43
    events
    0.43
    empire
    0.43
    red
    0.42
    generational
    0.42
    anaf
    0.42
    Activations Density 0.021%

    No Known Activations