© 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. 223306
    Prev
    Next
    INDEX
    Explanations

    from dying

    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
     indipendente
    0.46
     independiente
    0.45
    獨立
    0.44
     독립
    0.43
     independientes
    0.41
    🥸
    0.40
    trt
    0.40
    तोंडा
    0.39
     엄
    0.39
     dentées
    0.39
    POSITIVE LOGITS
    це
    0.38
    uest
    0.37
    Quiet
    0.37
     quiet
    0.35
     Oasis
    0.35
     catch
    0.34
     serene
    0.34
     monit
    0.34
     competing
    0.34
     compete
    0.33
    Activations Density 0.000%

    No Known Activations