© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29784
    Prev
    Next
    INDEX
    Explanations

    take back

    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
     novo
    0.48
    mayın
    0.40
     σκ
    0.39
    屻
    0.39
    QUIN
    0.38
    দিন
    0.38
    味が
    0.38
    日前
    0.38
     refinery
    0.38
    🦐
    0.37
    POSITIVE LOGITS
     Spectral
    0.40
    érieures
    0.39
     dispensing
    0.36
     dispensed
    0.36
    ített
    0.35
     Übersetzung
    0.35
     espectáculo
    0.35
     hassle
    0.34
    Spectral
    0.34
     goc
    0.34
    Activations Density 0.000%

    No Known Activations