© 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. 45429
    Prev
    Next
    INDEX
    Explanations

    generally relaxed

    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
     ло
    0.46
     воспа
    0.45
    朹
    0.45
    ניה
    0.44
     kebak
    0.44
     жыл
    0.43
    傕
    0.43
     грн
    0.43
     Sementara
    0.42
     çap
    0.42
    POSITIVE LOGITS
    unless
    0.52
     apparel
    0.45
     facilities
    0.45
     editions
    0.43
     newsletters
    0.43
    robe
    0.42
     Facilities
    0.42
    facilities
    0.41
    rom
    0.41
    x
    0.40
    Activations Density 0.003%

    No Known Activations