© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225378
    Prev
    Next
    INDEX
    Explanations

    regularly, rotation, values, uncertain, energy, protocols, subconscious

    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
     Edg
    0.47
     oWord
    0.46
    ﹗
    0.46
    BlockUsed
    0.45
    疝
    0.45
     vutt
    0.45
     poprzed
    0.44
    !“
    0.43
    。『
    0.43
     havde
    0.43
    POSITIVE LOGITS
    6
    0.55
    db
    0.54
    degrees
    0.54
    n
    0.54
    y
    0.52
    t
    0.52
    h
    0.52
    5
    0.52
    l
    0.51
    1
    0.51
    Activations Density 0.001%

    No Known Activations