© 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. 16-GEMMASCOPE-2-RES-65K
    7. 1437
    Prev
    Next
    INDEX
    Explanations

    Douglas Adams +1/+1 counters

    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_65k_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
    Gut
    0.48
    ล
    0.48
    Gamma
    0.48
    Piano
    0.47
    نى
    0.46
    ல்
    0.46
     پارٹی
    0.45
    نی
    0.45
    Read
    0.44
    Travel
    0.44
    POSITIVE LOGITS
     vorhand
    0.52
     வயது
    0.52
     befol
    0.50
     bestimmten
    0.49
    ucceeded
    0.49
    .³
    0.49
     perfused
    0.49
    <unused2018>
    0.49
     攵
    0.48
    
    0.48
    Activations Density 0.001%

    No Known Activations