© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16707
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    oh
    0.49
    。
    0.46
    seab
    0.46
    loaf
    0.46
    irmat
    0.43
    。(
    0.42
    theater
    0.42
    snow
    0.42
    ។
    0.42
    surprisingly
    0.41
    POSITIVE LOGITS
     sempre
    0.55
     inoltre
    0.55
     visitante
    0.54
     belli
    0.51
     thiệt
    0.51
     siempre
    0.50
     pedir
    0.50
     wykony
    0.50
     punti
    0.49
     abaste
    0.48
    Activations Density 0.015%

    No Known Activations