© 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. 142797
    Prev
    Next
    INDEX
    Explanations

    Opening Ceremony, crowdedness, informe de

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

    Glacier storage and advantage on checks

    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
    4
    0.57
    7
    0.47
    legacy
    0.46
    Artifact
    0.46
    matrix
    0.46
     சே
    0.45
     decidedly
    0.43
     रचना
    0.43
    MATRIX
    0.43
     Hungary
    0.42
    POSITIVE LOGITS
    jší
    0.55
    elung
    0.44
    لڈ
    0.43
    υτό
    0.43
     sensit
    0.41
    èt
    0.41
    蓖
    0.41
     pribadi
    0.40
    edere
    0.40
    cą
    0.40
    Activations Density 0.000%

    No Known Activations