© 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. 149595
    Prev
    Next
    INDEX
    Explanations

    turn-taking, posture breaking

    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
    Metaxy
    0.91
     ingeniería
    0.88
     história
    0.88
    <unused2142>
    0.87
    ܗ
    0.87
     реконструк
    0.86
    ȟ
    0.85
     gén
    0.85
    <unused400>
    0.85
     будущем
    0.85
    POSITIVE LOGITS
    als
    0.71
    amientos
    0.70
     value
    0.68
     conditions
    0.68
    ized
    0.66
    Value
    0.66
    Layer
    0.66
     Single
    0.65
     single
    0.65
    ense
    0.65
    Activations Density 0.000%

    No Known Activations