© 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. 14328
    Prev
    Next
    INDEX
    Explanations

    refusing exploitative or harmful content

    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
    uia
    3.83
    ン
    3.73
    संख्यक
    3.47
    й
    3.36
    ल
    3.07
    ія
    3.06
    м
    3.04
    i
    3.03
    uole
    2.99
    aný
    2.99
    POSITIVE LOGITS
    translated
    2.76
    ding
    2.03
    േക്ക്
    2.03
     “
    1.98
    <em>
    1.96
    리즈
    1.93
    𝘆
    1.89
     -$
    1.88
    𝗹
    1.87
    ൂടെ
    1.86
    Activations Density 0.002%

    No Known Activations