© 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. 163693
    Prev
    Next
    INDEX
    Explanations

    institutional audits

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

    why called pirates

    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
    είου
    0.51
    ף
    0.47
    慨
    0.47
     Gracie
    0.45
     बोले
    0.45
     previa
    0.44
     Ramsay
    0.44
     premat
    0.44
     মস্ক
    0.43
    ステム
    0.43
    POSITIVE LOGITS
     interventions
    0.49
    andelion
    0.47
     intervention
    0.47
     thefts
    0.46
    -‘
    0.46
     october
    0.46
    rep
    0.45
     attrs
    0.45
    ᱣ
    0.45
    been
    0.43
    Activations Density 0.001%

    No Known Activations