© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 74996
    Prev
    Next
    INDEX
    Explanations

    quantities and units

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

    counting and arithmetic problems

    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
     Mixture
    0.45
     lè
    0.45
     mixture
    0.44
     &:
    0.43
     Theoretically
    0.42
    の場合
    0.41
    ),(
    0.41
     (<
    0.41
     vals
    0.41
     αντί
    0.40
    POSITIVE LOGITS
    conservation
    0.43
    ገኛ
    0.42
    ඉ
    0.42
    getImageFolder
    0.40
    GroupId
    0.40
    widgetTo
    0.39
    addChild
    0.39
    굿
    0.39
    Тре
    0.39
    लरशिप
    0.38
    Activations Density 0.002%

    No Known Activations