© 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
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148869
    Prev
    Next
    INDEX
    Explanations

    pytorch nn and cuda

    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
     স্ক
    0.64
    거
    0.62
    framework
    0.62
     것
    0.61
    Recording
    0.60
    war
    0.59
    epsilon
    0.59
    桀
    0.58
    tracks
    0.58
    Ped
    0.57
    POSITIVE LOGITS
     Shoot
    0.85
    PreviewSize
    0.83
     Shooter
    0.83
     Cyan
    0.81
     Zoom
    0.81
    inib
    0.80
    റെ
    0.80
    పోయింది
    0.79
     UNIV
    0.79
     shooter
    0.77
    Activations Density 0.002%

    No Known Activations