© 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. 22-GEMMASCOPE-2-RES-262K
    4. 4946
    Prev
    Next
    INDEX
    Explanations

    Bear, code, equations, completely

    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_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
     dvar
    0.93
    菌
    0.87
    冪
    0.87
    jgl
    0.85
     açıklam
    0.81
    𝚓
    0.80
    ເວ
    0.79
    VERTISEMENT
    0.78
     fact
    0.78
    拋
    0.76
    POSITIVE LOGITS
     inguinal
    0.64
    িতা
    0.63
    ஸ்த
    0.62
    \|_{\
    0.62
     Ze
    0.62
     '</
    0.61
    Fala
    0.60
     anderen
    0.60
     सुरुवात
    0.59
     день
    0.58
    Activations Density 0.000%

    No Known Activations