© 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-65K
    7. 40993
    Prev
    Next
    INDEX
    Explanations

    defining classes and macros

    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_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
     messaggio
    0.50
     메시
    0.49
    فكير
    0.49
     నిర్మాత
    0.49
     mensaje
    0.49
    感动
    0.48
     క
    0.47
     لص
    0.47
     ష
    0.46
    Mum
    0.46
    POSITIVE LOGITS
    MathOperator
    0.50
     several
    0.44
    ophosphate
    0.44
     California
    0.43
     g
    0.42
    ./
    0.41
     Calif
    0.40
     Spain
    0.40
    {
    0.40
    s
    0.40
    Activations Density 0.002%

    No Known Activations