© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 40161
    Prev
    Next
    INDEX
    Explanations

    what specific information

    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_16_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
     ツ
    0.65
     โดย
    0.64
     लेकिन
    0.63
     لیکن
    0.61
     个
    0.60
     tylko
    0.59
    íe
    0.59
     -
    0.58
    による
    0.58
    する
    0.58
    POSITIVE LOGITS
    soever
    0.60
    passt
    0.57
    cknow
    0.57
    e
    0.55
     föret
    0.51
    Could
    0.50
    боли
    0.50
    COVID
    0.50
     Mapper
    0.50
    ಿಸಿದೆ
    0.50
    Activations Density 0.121%

    No Known Activations