© 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. 48350
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code snippets

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

    comma followed by err

    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
    anatom
    0.49
    pal
    0.44
     귀
    0.44
    switcher
    0.44
    emphasis
    0.43
    连锁
    0.43
    귀
    0.42
    formula
    0.42
    svet
    0.41
    bolos
    0.41
    POSITIVE LOGITS
     consenso
    0.46
     :=
    0.43
    ковой
    0.43
     Almanac
    0.42
     consens
    0.42
     Аль
    0.41
    候选
    0.41
    ія
    0.40
     Ally
    0.40
    
    0.39
    Activations Density 0.000%

    No Known Activations