© 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. 30512
    Prev
    Next
    INDEX
    Explanations

    counts for download statistics

    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
    mäßige
    0.46
    στε
    0.45
    գ
    0.44
    prach
    0.43
    се
    0.43
    तील
    0.42
    本来
    0.41
    書館
    0.41
    =$
    0.40
    зад
    0.40
    POSITIVE LOGITS
     peł
    0.50
     pause
    0.50
     Metals
    0.48
     preparedness
    0.47
    audio
    0.46
     failures
    0.46
    ik
    0.46
    es
    0.46
     audio
    0.45
     Sic
    0.44
    Activations Density 0.001%

    No Known Activations