© 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. 153706
    Prev
    Next
    INDEX
    Explanations

    it is [descriptor]

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

    is followed by a description

    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
    鲅
    0.42
    мі
    0.41
    elementProp
    0.41
    iters
    0.40
     همین
    0.40
    โพ
    0.39
    lich
    0.39
     Віль
    0.39
    МІ
    0.39
    >("
    0.38
    POSITIVE LOGITS
     fungus
    0.48
     coincidence
    0.46
     ulcer
    0.45
     crisis
    0.43
     extinction
    0.42
     হওয়ার
    0.42
     UV
    0.41
     nightmare
    0.41
     ug
    0.41
     UTI
    0.40
    Activations Density 0.001%

    No Known Activations