© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92073
    Prev
    Next
    INDEX
    Explanations

    read disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     Perman
    0.49
     intracranial
    0.46
     unsurpassed
    0.44
    Helen
    0.43
    </i>
    0.42
    ствовать
    0.42
    ровала
    0.42
     intrauterine
    0.41
     karst
    0.41
     perman
    0.40
    POSITIVE LOGITS
    ات
    0.51
     ឬ
    0.49
     灯
    0.46
    ů
    0.46
    λα
    0.45
    燈
    0.45
    ✬
    0.44
     sprzedaży
    0.44
    rizioni
    0.44
    
    0.44
    Activations Density 0.003%

    No Known Activations