© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15115
    Prev
    Next
    INDEX
    Explanations

    hypnosis

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DETA
    0.55
    দিনে
    0.54
     hø
    0.52
    Day
    0.52
    hyper
    0.52
    tope
    0.51
     hyper
    0.50
     초
    0.50
     DETA
    0.50
    λια
    0.50
    POSITIVE LOGITS
     hyp
    1.98
     Hyp
    1.98
    Hyp
    1.83
    hyp
    1.77
     hypo
    1.67
     hypoc
    1.46
     hypnosis
    1.37
     hip
    1.28
     Hip
    1.24
     hypoth
    1.21
    Activations Density 0.017%

    No Known Activations