© 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. 193391
    Prev
    Next
    INDEX
    Explanations

    foreign characters and phrases

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

    generating sequences, itineraries, or plans

    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
    ケーション
    0.47
     remedies
    0.46
    novation
    0.46
    註
    0.44
    jesi
    0.44
    結婚
    0.44
    merzen
    0.43
     established
    0.43
    解決
    0.43
     adjudication
    0.42
    POSITIVE LOGITS
    ICH
    0.50
    ÈME
    0.48
    ”（
    0.47
    ORT
    0.46
    UMBIA
    0.44
    洱
    0.44
    toDouble
    0.44
    ILLE
    0.44
     хранения
    0.44
    ENTA
    0.43
    Activations Density 0.001%

    No Known Activations