© 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. 455
    Prev
    Next
    INDEX
    Explanations

    common article or determiner following prepositions

    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
    。
    0.91
     F
    0.85
     maar
    0.85
    V
    0.84
    ।
    0.83
    but
    0.82
    ։
    0.82
     T
    0.82
    F
    0.82
     D
    0.79
    POSITIVE LOGITS
    此之外
    1.29
    此同时
    1.04
    heureusement
    0.99
    credibly
    0.86
     δὲ
    0.85
    <unused2165>
    0.85
    credible
    0.85
    noons
    0.85
     ､
    0.84
    Mard
    0.83
    Activations Density 0.578%

    No Known Activations