© 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. 102123
    Prev
    Next
    INDEX
    Explanations

    foreign words and orchestras

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

    risk, questions, options

    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
     Blackboard
    0.48
     Notify
    0.46
    瓠
    0.45
     తనకు
    0.44
    ဆေး
    0.44
     ఒక
    0.44
    婺
    0.43
    罣
    0.43
     సంబంధ
    0.43
     הד
    0.42
    POSITIVE LOGITS
    arsi
    0.50
     treasures
    0.46
    =(-
    0.45
     cherche
    0.45
    лях
    0.43
    ando
    0.43
    )=(-
    0.42
     orchestras
    0.42
    ারা
    0.42
    ます
    0.41
    Activations Density 0.001%

    No Known Activations