© 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. 94264
    Prev
    Next
    INDEX
    Explanations

    mission starting

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

    additive color

    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
    2
    0.46
     training
    0.44
     practic
    0.44
     dies
    0.44
     terl
    0.44
     apprenticeship
    0.43
    REG
    0.42
     sampler
    0.42
     stain
    0.42
     mirror
    0.41
    POSITIVE LOGITS
    ufieurs
    0.52
    خفض
    0.51
    阖
    0.51
     Erwachsene
    0.50
     अजि
    0.50
     Ekim
    0.50
    的变化
    0.49
    ewnątrz
    0.49
    Congrats
    0.49
    闔
    0.49
    Activations Density 0.001%

    No Known Activations