© 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. 10456
    Prev
    Next
    INDEX
    Explanations

    Sci-fi genre

    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
     қу
    1.21
     Sheikh
    1.08
     Lash
    1.06
     탈
    1.06
     khat
    1.02
     Osman
    1.02
     Somali
    1.02
     Saeed
    0.98
     Lombok
    0.98
     palav
    0.94
    POSITIVE LOGITS
     IU
    1.40
     Anambra
    1.24
     Nw
    1.24
    ị
    1.20
     ndị
    1.16
    Nw
    1.16
     bụ
    1.16
     Igbo
    1.14
     Chuk
    1.11
    Ụ
    1.10
    Activations Density 0.039%

    No Known Activations