© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14694
    Prev
    Next
    INDEX
    Explanations

    dark fantasy, academia, chocolate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    ℗
    1.07
    ಿಕ
    1.04
     δικ
    1.03
    Left
    1.01
    going
    0.93
     Executives
    0.92
     LUCKY
    0.91
     staggering
    0.89
    phant
    0.88
    何
    0.88
    POSITIVE LOGITS
     chocolate
    1.30
     confidentialité
    1.23
     haired
    1.22
     चॉकलेट
    1.17
    เนิน
    1.16
    chocolate
    1.14
     brooding
    1.14
     шокола
    1.10
    er
    1.08
    黢
    1.08
    Activations Density 0.041%

    No Known Activations