© 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. 161017
    Prev
    Next
    INDEX
    Explanations

    numbers and words like citizen

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

    multiplication and division

    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
     grueso
    0.47
     నిర్మాణ
    0.47
    ដែល
    0.46
    อยาก
    0.45
    髡
    0.44
     Wool
    0.43
     unwarranted
    0.43
    coelastic
    0.43
     repaso
    0.43
     diejenigen
    0.43
    POSITIVE LOGITS
    zero
    0.50
    y
    0.50
    x
    0.47
    ]["
    0.46
    q
    0.46
    ｘ
    0.46
    abc
    0.45
    2
    0.45
    mys
    0.44
    ers
    0.44
    Activations Density 0.000%

    No Known Activations