© 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. 31-GEMMASCOPE-2-RES-262K
    7. 139493
    Prev
    Next
    INDEX
    Explanations

    topic discussion starters

    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
    の為
    0.43
     روند
    0.43
    plas
    0.42
     />
    0.42
    bond
    0.42
     merken
    0.42
     홈
    0.41
     #:
    0.41
     vuole
    0.41
    _
    0.41
    POSITIVE LOGITS
    ಲ್ಲು
    0.46
    ုတ်
    0.46
    графии
    0.45
     opposing
    0.44
    肃
    0.44
    ণার
    0.43
    сил
    0.42
    ೋಗ್ಯ
    0.42
    肅
    0.42
     historical
    0.42
    Activations Density 0.004%

    No Known Activations