© 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. 32084
    Prev
    Next
    INDEX
    Explanations

    profit, customer, control, suits

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

    finding non-trivial factors

    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
    등
    0.43
    ประกอบ
    0.42
    -
    0.42
    iei
    0.41
     colorido
    0.41
    v
    0.40
    쥬
    0.40
     Y
    0.39
    软
    0.39
     библиоте
    0.38
    POSITIVE LOGITS
    marshalN
    0.54
    DataTable
    0.50
     −/−
    0.47
     togg
    0.47
    marshalO
    0.47
     ingot
    0.47
     CCSDT
    0.47
     કા
    0.46
     கட்டமை
    0.46
     overcrow
    0.45
    Activations Density 0.000%

    No Known Activations