© 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. 193637
    Prev
    Next
    INDEX
    Explanations

    conference.PowerPoint needslegends.to hireinto aReef areenabling retrievalbecome professionalbeginning to

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

    programming and locations

    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
    ོས་
    0.49
    䍜
    0.47
     গ্রামবাস
    0.46
     Preventing
    0.45
    சே
    0.44
     Thành
    0.44
    ུ་
    0.44
     finalists
    0.43
     Yamazaki
    0.43
    枒
    0.43
    POSITIVE LOGITS
    n
    0.59
    m
    0.54
    dashed
    0.53
    mir
    0.52
    ir
    0.50
    o
    0.49
    st
    0.48
    sp
    0.48
    lm
    0.47
    window
    0.47
    Activations Density 0.002%

    No Known Activations