© 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. 168358
    Prev
    Next
    INDEX
    Explanations

    Identity, future, technical terms

    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
    HIP
    0.44
    ாவின்
    0.41
    ᄉ
    0.40
    hawks
    0.40
    िप्स
    0.40
    సా
    0.40
    MenuItem
    0.39
    setAutoDraw
    0.39
    amam
    0.38
     қара
    0.38
    POSITIVE LOGITS
     condoms
    0.47
     định
    0.46
     saints
    0.45
     Ebola
    0.45
     tyl
    0.45
     connaître
    0.45
     ઇ
    0.45
     ubuntu
    0.45
     acheter
    0.44
     obituary
    0.44
    Activations Density 0.004%

    No Known Activations