© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9667
    Prev
    Next
    INDEX
    Explanations

    factor driving

    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_262k_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
    
    2.24
    𝓀
    2.23
     dotyczą
    2.19
    ía
    2.18
     firmness
    2.16
    উল্লেখ্য
    2.16
     isLoading
    2.14
    followfollow
    2.13
    нибудь
    2.09
     стро
    2.08
    POSITIVE LOGITS
     listrik
    2.87
    िंग
    2.73
    ح
    2.67
    hashtag
    2.64
    തിരെ
    2.63
    人
    2.54
    情况下
    2.36
    cled
    2.35
    nze
    2.33
    пи
    2.29
    Activations Density 0.138%

    No Known Activations