© 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. 88066
    Prev
    Next
    INDEX
    Explanations

    shall be incorporated

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

    terraccota army, trials, code, mourning bell

    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
    S
    0.63
    H
    0.55
    إن
    0.54
    ا
    0.53
    C
    0.51
    P
    0.51
    J
    0.50
    П
    0.50
    인
    0.50
    Ş
    0.49
    POSITIVE LOGITS
     dichloromethane
    0.59
     subtlet
    0.54
     dichlor
    0.50
    attet
    0.48
     পরম
    0.47
    toa
    0.47
    idoarjo
    0.47
    snacks
    0.46
     표
    0.46
    hitth
    0.46
    Activations Density 0.001%

    No Known Activations