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. 22-GEMMASCOPE-2-RES-16K
    4. 9472
    Prev
    Next
    INDEX
    Explanations

    plus sign and math operations

    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_22_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
     समझा
    1.69
    ה
    1.53
     remettre
    1.49
     মতো
    1.43
    +}$
    1.43
    पृ
    1.38
    ్వ
    1.38
     सिद्धांतों
    1.34
    +
    1.34
     Kxc
    1.33
    POSITIVE LOGITS
    /−
    2.69
    /-}$
    2.00
    チック
    1.97
    _+
    1.94
     tard
    1.80
    ---------------+
    1.74
     (+)
    1.74
     tôt
    1.64
    acre
    1.64
    &+
    1.58
    Activations Density 0.116%

    No Known Activations