© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19405
    Prev
    Next
    INDEX
    Explanations

    purpose, target, or decision

    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
     maravill
    0.42
     rationalize
    0.40
    澈
    0.40
    樂
    0.39
    更大
    0.39
     అయినా
    0.39
     marvellous
    0.38
     】,
    0.38
    ၷ
    0.38
     subsection
    0.38
    POSITIVE LOGITS
    γο
    0.49
    тів
    0.48
    ત્તા
    0.48
     формы
    0.47
    bury
    0.47
    с
    0.46
    ية
    0.45
    inių
    0.45
    ҳои
    0.45
    ंसाठी
    0.45
    Activations Density 0.000%

    No Known Activations