Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7242
    Prev
    Next
    INDEX
    Explanations

    vasculature and related conditions

    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
    र
    3.64
    ні
    3.10
    ty
    3.01
    м
    2.99
     Toutefois
    2.81
    მ
    2.80
    ดู
    2.80
    ش
    2.76
    ریشن
    2.75
    पंजा
    2.71
    POSITIVE LOGITS
    𝘨
    3.30
     uncountable
    3.17
    𝚐
    2.94
    ب
    2.92
    identifier
    2.90
    yrus
    2.86
     êtes
    2.86
    ಿಕ್
    2.82
    ্কর
    2.80
     tau
    2.76
    Activations Density 0.020%

    No Known Activations