© 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. 56972
    Prev
    Next
    INDEX
    Explanations

    coffee, laughing, thrilling, overgrown

    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
    repository
    0.48
    ms
    0.43
    with
    0.42
    trans
    0.41
    documentation
    0.41
     actuators
    0.41
    m
    0.40
     adsorbent
    0.40
     strangely
    0.40
    funct
    0.40
    POSITIVE LOGITS
     🥰
    0.51
    哪怕
    0.48
     بينما
    0.47
     throwIfNotFound
    0.45
     ❤️
    0.44
    !»
    0.44
     Elsewhere
    0.44
     Enquanto
    0.44
     😍
    0.43
     днем
    0.43
    Activations Density 0.006%

    No Known Activations