© 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. 343
    Prev
    Next
    INDEX
    Explanations

    final answer is

    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
    y
    3.31
    ي
    3.19
    er
    3.19
    र
    2.71
    s
    2.67
    يّ
    2.55
    l
    2.28
    ০
    2.21
    es
    2.19
    র
    2.14
    POSITIVE LOGITS
     frictions
    2.66
    勳
    2.46
     дина
    2.45
     lustre
    2.41
    <unused1898>
    2.41
    <unused1145>
    2.39
    <unused1029>
    2.37
     prismatic
    2.37
    destroyEach
    2.34
     图
    2.33
    Activations Density 2.179%

    No Known Activations