© 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. 22-GEMMASCOPE-2-RES-262K
    4. 5130
    Prev
    Next
    INDEX
    Explanations

    names of organizations or institutions

    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_22_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
    and
    0.75
    items
    0.70
     shader
    0.67
    noise
    0.66
    those
    0.65
    item
    0.65
     items
    0.65
    =-
    0.65
    wallet
    0.64
    ar
    0.64
    POSITIVE LOGITS
     United
    1.07
     National
    1.00
     Institute
    0.96
     International
    0.96
     Servicio
    0.92
     Office
    0.89
     Musée
    0.88
     Canadian
    0.88
     Metropolitan
    0.88
     Federación
    0.88
    Activations Density 0.125%

    No Known Activations