© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14109
    Prev
    Next
    INDEX
    Explanations

    ขอวิธี

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused1407>
    3.19
    <unused831>
    3.14
    ंगाबाद
    3.01
    <unused1273>
    2.98
    <unused809>
    2.95
    獧
    2.94
    atrième
    2.89
    <unused1392>
    2.88
    <unused1501>
    2.87
    <unused1341>
    2.86
    POSITIVE LOGITS
    ඝ
    2.48
    ‘
    2.33
    érables
    2.30
    ds
    2.23
    <u>
    2.14
     Up
    2.13
    rj
    2.12
    <0x0D>
    2.12
    j
    2.11
    ඥ
    2.11
    Activations Density 0.008%

    No Known Activations