© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86624
    Prev
    Next
    INDEX
    Explanations

    alleged Communists, look at, stand displays

    np_acts-logits-general · gemini-2.5-flash-lite

    risks and complications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     어린
    0.44
     члены
    0.43
     alakalı
    0.43
     sphincter
    0.42
    包人
    0.41
    лис
    0.41
     pluripotent
    0.41
    绝
    0.41
     territor
    0.41
     Алек
    0.41
    POSITIVE LOGITS
    media
    0.47
    beautiful
    0.46
    can
    0.45
    minute
    0.44
     Conven
    0.44
    makes
    0.44
     Telev
    0.44
    gives
    0.44
    find
    0.43
    1
    0.43
    Activations Density 0.000%

    No Known Activations