© 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. 14412
    Prev
    Next
    INDEX
    Explanations

    explicitly specify

    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
    ى
    2.52
    نش
    2.48
    ی
    2.48
     сразу
    2.43
    เสริม
    2.37
    ശാസ്ത്ര
    2.31
     даже
    2.31
     проведен
    2.27
    পত্র
    2.26
    ભગ
    2.25
    POSITIVE LOGITS
    ｔ
    2.31
     égard
    2.21
    𝚝
    2.20
    𝚛
    2.02
    therly
    2.01
     toa
    1.95
    ারের
    1.95
     `"
    1.94
    ɗ
    1.94
    Ԁ
    1.94
    Activations Density 0.017%

    No Known Activations