© 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. 199709
    Prev
    Next
    INDEX
    Explanations

    ownership and sales

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

    remote access and data operations

    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
    昔
    0.52
     pozit
    0.51
    不安定
    0.49
    成熟
    0.49
    冷静
    0.49
    适合
    0.48
    גו
    0.48
     чаще
    0.48
    Биография
    0.47
    阔
    0.47
    POSITIVE LOGITS
     Ownership
    0.58
     Verkauf
    0.55
     their
    0.54
     ownership
    0.52
    opened
    0.52
     Owners
    0.51
     owners
    0.50
     وف
    0.50
     sette
    0.49
     Messrs
    0.49
    Activations Density 0.003%

    No Known Activations