© 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. 31-GEMMASCOPE-2-RES-262K
    7. 11340
    Prev
    Next
    INDEX
    Explanations

    replace

    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_31_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
     schre
    0.43
     mantra
    0.42
     accompanying
    0.41
     interpretive
    0.41
     storytelling
    0.41
     accompan
    0.40
     يزيد
    0.40
    猙
    0.40
     glaube
    0.39
     anthropology
    0.39
    POSITIVE LOGITS
    替换
    0.78
     remplacement
    0.73
    replace
    0.73
     replacing
    0.72
    Replacing
    0.69
     substituir
    0.67
     substitution
    0.66
     seamlessly
    0.66
     replace
    0.66
     replaces
    0.65
    Activations Density 0.095%

    No Known Activations