© 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. 168753
    Prev
    Next
    INDEX
    Explanations

    risk of, code representing, The Green

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

    approach than

    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
    v
    0.54
     Cavendish
    0.48
     gode
    0.47
     بے
    0.47
     ferv
    0.47
     eventualmente
    0.47
     Russia
    0.46
     buen
    0.46
     Mard
    0.46
     Vysok
    0.45
    POSITIVE LOGITS
     prepping
    0.55
    檚
    0.55
    ètement
    0.48
    árias
    0.47
     buttons
    0.46
    iseren
    0.45
    ᇁ
    0.45
    鑑
    0.45
    ႄ
    0.44
    ოვანი
    0.43
    Activations Density 0.002%

    No Known Activations