© 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-16K
    7. 10033
    Prev
    Next
    INDEX
    Explanations

    per frame, year, month

    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_16k_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
    倸
    1.12
     artyku
    0.98
     соста
    0.96
    ಊ
    0.92
     miércoles
    0.92
     веще
    0.90
     avevo
    0.89
     #+#
    0.89
     mochila
    0.89
     coveredmethods
    0.89
    POSITIVE LOGITS
     political
    0.61
     particular
    0.59
    Kris
    0.59
     transparent
    0.56
     budgetary
    0.56
     specific
    0.56
     promptly
    0.56
    Catal
    0.55
    一大
    0.55
     key
    0.55
    Activations Density 0.003%

    No Known Activations