© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35110
    Prev
    Next
    INDEX
    Explanations

    technical concepts and parameters

    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_40_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
    listed
    0.42
    
    0.42
    rian
    0.38
    ],\
    0.36
    wale
    0.36
    ños
    0.35
    "]},{"
    0.35
    瞌
    0.35
    ಿಸಿ
    0.35
    eter
    0.35
    POSITIVE LOGITS
    ैग
    0.40
     willingly
    0.39
     ice
    0.38
    ాయి
    0.38
     mathcolor
    0.37
    ៃ
    0.37
     storylines
    0.37
     desarrollando
    0.37
     allure
    0.36
    向量
    0.36
    Activations Density 0.000%

    No Known Activations