© 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. 74616
    Prev
    Next
    INDEX
    Explanations

    examples or descriptions

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

    chopped list preserved

    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
    fälle
    0.42
     diphtheria
    0.40
     സ്ഥാപ
    0.40
     останови
    0.39
    숲
    0.39
     ආහාර
    0.39
    Stopped
    0.39
     weakest
    0.39
     FARM
    0.39
    Ꮂ
    0.39
    POSITIVE LOGITS
    ographer
    0.50
    稿
    0.44
    生まれ
    0.43
     অন্ত
    0.40
    LLY
    0.40
    writers
    0.40
    osex
    0.39
    awesi
    0.39
    osan
    0.39
    ORTS
    0.39
    Activations Density 0.000%

    No Known Activations