© 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. 207181
    Prev
    Next
    INDEX
    Explanations

    time, duration, or conditions

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

    ninja style, south park

    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
    nutrient
    0.53
     பொருளாதார
    0.51
    agricult
    0.50
    ,}
    0.48
    rime
    0.47
    environmental
    0.47
    economic
    0.47
    rill
    0.47
    uer
    0.46
    theorem
    0.46
    POSITIVE LOGITS
     privy
    0.46
    ст
    0.46
     stk
    0.46
    赦
    0.45
     disturbs
    0.42
     balloons
    0.41
     mickey
    0.41
    GCG
    0.41
    前面的
    0.41
    aced
    0.40
    Activations Density 0.000%

    No Known Activations