© 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. 35691
    Prev
    Next
    INDEX
    Explanations

    Python code and keywords

    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
    2
    0.61
    3
    0.54
    4
    0.52
    7
    0.49
    1
    0.49
    .
    0.48
    i
    0.47
    ين
    0.46
    تا
    0.46
    V
    0.46
    POSITIVE LOGITS
     практику
    0.50
    🅻
    0.50
    リビング
    0.49
    돼
    0.49
     jokingly
    0.49
    गेशन
    0.48
     configur
    0.47
     ऑफिस
    0.47
     гото
    0.47
     системе
    0.47
    Activations Density 0.008%

    No Known Activations