© 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. 29-GEMMASCOPE-2-RES-262K
    4. 149500
    Prev
    Next
    INDEX
    Explanations

    nearing expiration date or weary eyes

    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_29_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
    stand
    0.81
    স্থাপ
    0.76
    sun
    0.76
     modulator
    0.74
    ര്‍ഷ
    0.74
     basal
    0.74
    }}^
    0.74
     mongodb
    0.72
    billing
    0.72
     signé
    0.71
    POSITIVE LOGITS
    дите
    0.66
     однозна
    0.65
    味的
    0.65
    津
    0.62
     Appeals
    0.60
    取り
    0.59
    ULS
    0.59
    味
    0.59
    圖
    0.58
     enseñar
    0.58
    Activations Density 0.002%

    No Known Activations