© 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. 152850
    Prev
    Next
    INDEX
    Explanations

    Cam Newton, Committee declared, Aisha

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

    increase was

    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
    Negative Logits
    ᵗ
    0.49
     dużo
    0.48
     multitudes
    0.48
    ທີ່
    0.47
     kills
    0.44
    zną
    0.43
     triglycerides
    0.42
    manın
    0.41
     estrem
    0.40
    _
    0.40
    POSITIVE LOGITS
    รียม
    0.46
    OLYBD
    0.45
    coloring
    0.44
    㣩
    0.43
    IR
    0.43
    舉
    0.42
    developing
    0.41
     coloring
    0.41
     ORDER
    0.41
    isty
    0.41
    Activations Density 0.000%

    No Known Activations