© 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. 112815
    Prev
    Next
    INDEX
    Explanations

    items, need, feats, Great, Areas, be

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

    following examples or similar structures

    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
    ي
    0.47
    ctions
    0.46
    oces
    0.46
    CTIONS
    0.45
     serez
    0.44
    י
    0.43
    ז
    0.43
    aths
    0.43
    कत
    0.42
    OCE
    0.42
    POSITIVE LOGITS
     Sapphire
    0.53
     Koordin
    0.51
    犄
    0.50
     Drugs
    0.49
     Standing
    0.48
     Mapping
    0.46
     sapphire
    0.46
     Wound
    0.46
     Си
    0.46
     Meeting
    0.45
    Activations Density 0.001%

    No Known Activations