© 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. 1424
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and specifications

    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
    born
    0.70
     Filed
    0.65
    estine
    0.63
     railroad
    0.62
    খ
    0.62
     Born
    0.61
    属
    0.60
     born
    0.60
    emarks
    0.60
     race
    0.58
    POSITIVE LOGITS
    5
    0.99
    max
    0.98
     выбран
    0.97
     পঞ্চাশ
    0.97
     ৫০০
    0.95
    ੫
    0.93
     डेढ़
    0.92
     पचास
    0.91
    Filter
    0.91
    threshold
    0.90
    Activations Density 0.782%

    No Known Activations