© 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. 14420
    Prev
    Next
    INDEX
    Explanations

    prepare students

    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
    و
    2.84
    상
    2.45
    ্
    2.28
    an
    2.27
    n
    2.16
    ا
    2.14
    爲
    2.09
    상은
    2.09
    kon
    2.09
    다는
    2.06
    POSITIVE LOGITS
     آفیسر
    2.74
    NEAR
    2.68
     cuello
    2.61
     jdbcTemplate
    2.59
    Enemy
    2.58
    JO
    2.56
    Autres
    2.54
    BRE
    2.52
     enthalpy
    2.50
     breaches
    2.50
    Activations Density 0.007%

    No Known Activations