© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10296
    Prev
    Next
    INDEX
    Explanations

    seemed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
    ഡിയ
    0.83
     dét
    0.78
    DH
    0.78
    idaire
    0.77
    DD
    0.76
    ด
    0.75
    <0x93>
    0.75
     Driscoll
    0.75
    叱
    0.74
     DH
    0.73
    POSITIVE LOGITS
     traits
    0.93
     prophecies
    0.86
     Traits
    0.85
     Psalms
    0.84
     PCs
    0.84
     apps
    0.84
     Projects
    0.84
     Plata
    0.84
     Leib
    0.84
     planets
    0.83
    Activations Density 0.135%

    No Known Activations