© 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-65K
    7. 385
    Prev
    Next
    INDEX
    Explanations

    sqlite3.connect(

    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_65k_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
     Span
    0.76
    graph
    0.75
     dow
    0.74
     sk
    0.74
     nepot
    0.73
    Gaussian
    0.72
     illusion
    0.72
    桑
    0.71
     ROI
    0.70
     misog
    0.69
    POSITIVE LOGITS
     установ
    0.87
     tenho
    0.81
     Durable
    0.78
     இருந்தாலும்
    0.76
     proprietors
    0.75
     tratamento
    0.74
    רץ
    0.73
    ဆို
    0.73
     resistente
    0.73
     wytr
    0.72
    Activations Density 0.003%

    No Known Activations