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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10461
    Prev
    Next
    INDEX
    Explanations

    constructive criticism, solutions, and feedback

    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_16k_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
    Кар
    1.13
     struktur
    1.11
    
    1.10
    Einstellungen
    1.05
    Ы
    1.04
    <unused2156>
    1.04
     latéral
    1.04
    ೮
    1.03
    𝗘
    1.03
     inferiores
    1.02
    POSITIVE LOGITS
    на
    1.23
    ivist
    1.16
    ית
    1.16
    از
    1.07
    al
    1.07
     أع
    1.05
    ivism
    1.04
    UsedError
    1.04
     dựng
    0.99
     indol
    0.97
    Activations Density 0.057%

    No Known Activations