© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90587
    Prev
    Next
    INDEX
    Explanations

    wave, pan, kitchen, CNN, cats

    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
    等待
    0.46
     finanz
    0.45
    mod
    0.44
    ixo
    0.43
    تاز
    0.43
    音
    0.42
    ției
    0.41
    陌
    0.40
    炁
    0.40
    ò
    0.40
    POSITIVE LOGITS
     landslides
    0.54
     uptick
    0.50
     plight
    0.49
     outskirts
    0.48
    rests
    0.48
     picnics
    0.48
     suburbs
    0.47
     Spacious
    0.47
     Likes
    0.46
    rsquo
    0.45
    Activations Density 0.004%

    No Known Activations