© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10362
    Prev
    Next
    INDEX
    Explanations

    Strengths and downsides

    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
    дравствуйте
    2.14
    SB
    1.71
    xu
    1.70
    BoxLayout
    1.65
    ISO
    1.64
    А
    1.63
     incluida
    1.62
    ricorn
    1.58
    achusetts
    1.56
    ného
    1.55
    POSITIVE LOGITS
    oretically
    3.72
    orems
    3.70
    ங்கிணை
    2.65
    י
    2.40
    swering
    2.32
    odore
    2.22
    credible
    2.18
    ри
    2.18
    xiety
    2.14
    пример
    2.04
    Activations Density 0.096%

    No Known Activations