© 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. 11542
    Prev
    Next
    INDEX
    Explanations

    columns in tables

    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
    িতে
    2.88
     muest
    2.75
     вот
    2.74
    elijke
    2.69
    紝
    2.65
    ຼ
    2.59
    ка
    2.53
    listView
    2.52
    isolate
    2.49
    algebra
    2.46
    POSITIVE LOGITS
    まま
    3.25
    ため
    3.09
    𝐩
    2.88
    en
    2.87
     eigenvectors
    2.85
     amps
    2.73
    তান্ত্রিক
    2.72
    𝙛
    2.65
    ément
    2.62
    𝙤
    2.61
    Activations Density 0.044%

    No Known Activations