© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12272
    Prev
    Next
    INDEX
    Explanations

    final answer calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Qxf
    0.43
    newlines
    0.42
     вулка
    0.42
    ကြည့်
    0.41
    ascape
    0.40
    hWnd
    0.39
    𝔯
    0.39
     이런
    0.39
     Lobkovic
    0.39
    lendi
    0.39
    POSITIVE LOGITS
     estimating
    0.50
    estimating
    0.50
     Estim
    0.49
     estimate
    0.48
    Estimation
    0.48
    Estimate
    0.47
     Estimate
    0.46
     estimated
    0.46
     Estimation
    0.46
    Estim
    0.43
    Activations Density 0.002%

    No Known Activations