© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10699
    Prev
    Next
    INDEX
    Explanations

    nuclear science and technology

    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
    داری
    2.92
    ić
    2.72
    ์
    2.65
    corsi
    2.64
    ele
    2.60
    یز
    2.58
    ം
    2.58
    esi
    2.56
    ी
    2.56
     wayside
    2.50
    POSITIVE LOGITS
    ⁧
    3.35
    ل
    3.33
    and
    2.92
    
    2.85
    𝑺
    2.76
    রার
    2.71
    un
    2.70
    ur
    2.69
    😂😂
    2.65
     librería
    2.59
    Activations Density 0.009%

    No Known Activations