© 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. 188367
    Prev
    Next
    INDEX
    Explanations

    pattern in lists

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

    list formatting

    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
     તેમાં
    0.53
    ્ય
    0.47
     potete
    0.46
    તમાં
    0.45
     કર્મ
    0.45
    、『
    0.45
    gyz
    0.44
    ፣
    0.44
    «,
    0.44
     පහ
    0.44
    POSITIVE LOGITS
     wallpapers
    0.50
     films
    0.46
    t
    0.46
     narrativa
    0.45
     wisata
    0.45
     porcel
    0.45
     기타
    0.44
     drywall
    0.44
    d
    0.44
     capsules
    0.43
    Activations Density 0.000%

    No Known Activations