© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 72
    Prev
    Next
    INDEX
    Explanations

    see someone/achieved/today/which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    и
    1.50
    üğünüz
    1.44
    ש
    1.39
     CGRectMake
    1.38
    ત
    1.33
     ја
    1.31
    최
    1.29
    Asimismo
    1.27
     вече
    1.26
     Efter
    1.24
    POSITIVE LOGITS
     xét
    2.09
     firsthand
    1.34
     tope
    1.23
    रेख
    1.14
     വഹ
    1.11
    PropTypes
    1.11
    ים
    1.11
    }$)
    1.10
     codons
    1.10
     horizonte
    1.07
    Activations Density 1.059%

    No Known Activations