© 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. 84202
    Prev
    Next
    INDEX
    Explanations

    moving average convergence divergence

    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
     Haemat
    0.38
     pigmented
    0.38
     Indigo
    0.38
     indigo
    0.38
    %",
    0.37
    ApiPath
    0.37
     anthocyan
    0.36
    礬
    0.36
     Gertrude
    0.36
     allergen
    0.36
    POSITIVE LOGITS
     divergence
    0.93
     divergences
    0.92
     diverges
    0.85
     diverg
    0.80
     diverge
    0.79
    diver
    0.78
     divergent
    0.75
     diver
    0.70
     divergents
    0.67
     Diver
    0.67
    Activations Density 0.010%

    No Known Activations