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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 19083
    Prev
    Next
    INDEX
    Explanations

    source code substitution

    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_53_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
     Residual
    1.11
     residual
    1.07
    Residual
    1.04
    residual
    0.96
     residuals
    0.93
    殘
    0.79
     Resident
    0.77
     resid
    0.74
    残
    0.74
     잔
    0.73
    POSITIVE LOGITS
    Rak
    0.46
     Viking
    0.45
    substitution
    0.41
     substitution
    0.39
    substituted
    0.39
     Rak
    0.38
     уй
    0.38
     విజ
    0.37
     Elm
    0.37
     substitutions
    0.36
    Activations Density 0.000%

    No Known Activations