© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11844
    Prev
    Next
    INDEX
    Explanations

    offering more details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     prazer
    0.77
     connaissances
    0.71
     voire
    0.71
     أو
    0.71
    泛
    0.70
     plaisir
    0.70
     vagy
    0.70
    爾
    0.68
    尔
    0.66
    NOWLEDGE
    0.66
    POSITIVE LOGITS
     insecure
    0.83
     बुलाया
    0.74
    рядок
    0.73
    leasing
    0.71
     frictions
    0.71
     
    0.71
     Fe
    0.69
     सीड
    0.69
     insecurity
    0.68
    Japan
    0.67
    Activations Density 0.010%

    No Known Activations