© 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. 60
    Prev
    Next
    INDEX
    Explanations

    a article + descriptive word

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

    alien planet

    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
    用
    0.54
    下的
    0.49
    ="'
    0.49
    劣
    0.47
    定了
    0.47
    必要
    0.46
    不安
    0.46
    店
    0.46
    ども
    0.43
    o
    0.43
    POSITIVE LOGITS
     effectuées
    0.49
     ballads
    0.48
     ძალი
    0.47
     resins
    0.46
    ies
    0.46
    yati
    0.46
     barcodes
    0.46
    केन
    0.45
     captions
    0.44
    udra
    0.44
    Activations Density 0.000%

    No Known Activations