© 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. 6198
    Prev
    Next
    INDEX
    Explanations

    Daybell

    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
    \
    0.35
      
    0.33
            
    0.33
     called
    0.31
     that
    0.31
     namely
    0.31
    C
    0.31
     which
    0.30
     \
    0.30
    =
    0.30
    POSITIVE LOGITS
     lovable
    0.45
     эмоциона
    0.41
     individualism
    0.40
     femininity
    0.39
     hatred
    0.38
     любви
    0.38
     uncompromising
    0.38
     unapolog
    0.38
     sonrisa
    0.37
     spirituality
    0.37
    Activations Density 0.141%

    No Known Activations