Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7331
    Prev
    Next
    INDEX
    Explanations

    programming keywords and declarations

    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
    t
    2.33
    ا
    2.26
    ة
    2.19
    te
    2.10
    caya
    1.97
    (",");
    1.87
    ed
    1.84
    tion
    1.79
    tel
    1.77
    tamil
    1.76
    POSITIVE LOGITS
     importantly
    2.43
     जिम्मेदार
    2.18
     outp
    2.03
    bearing
    2.00
    かも
    1.99
     emplacement
    1.94
    ॒
    1.92
    öd
    1.90
     tā
    1.89
    ;;)
    1.89
    Activations Density 0.070%

    No Known Activations