© 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. 38337
    Prev
    Next
    INDEX
    Explanations

    specific examples and generalizations

    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
    ﻮ
    0.52
    ﺪ
    0.49
    ள்ள
    0.45
     Kh
    0.41
    嬋
    0.41
    steil
    0.41
    )，
    0.40
     Screen
    0.39
    remmo
    0.39
     esimerkiksi
    0.38
    POSITIVE LOGITS
    expiration
    0.52
     ratification
    0.47
     heaviest
    0.46
     sweetest
    0.46
    overview
    0.46
     ésta
    0.45
    Backend
    0.45
    🤘
    0.45
    IGH
    0.44
    MEA
    0.44
    Activations Density 0.003%

    No Known Activations