© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8341
    Prev
    Next
    INDEX
    Explanations

    family member

    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_9_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
    ن
    3.17
    ির
    2.81
     successive
    2.76
    行う
    2.74
    お
    2.74
     deportivos
    2.65
     absenteeism
    2.59
    おか
    2.55
    वर
    2.55
    嚨
    2.54
    POSITIVE LOGITS
     siendo
    2.54
    ्राफी
    2.44
     대해서
    2.28
    cris
    2.27
     murmured
    2.23
    tois
    2.22
     inger
    2.20
    ১৮
    2.17
    ২২
    2.16
     royale
    2.13
    Activations Density 0.024%

    No Known Activations