© 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. 200546
    Prev
    Next
    INDEX
    Explanations

    blue textile

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

    loss and court cases

    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
    መሳሳይ
    0.51
    י
    0.49
     Revis
    0.47
    ي
    0.46
    海道
    0.45
    //!
    0.44
    ウト
    0.44
    ジング
    0.44
     Insertion
    0.44
    탁
    0.44
    POSITIVE LOGITS
     government
    0.51
    হরণ
    0.49
     küçük
    0.47
     naughty
    0.46
     lashes
    0.46
     monolith
    0.46
     fateful
    0.46
     أعلى
    0.45
     בית
    0.45
     ľud
    0.45
    Activations Density 0.000%

    No Known Activations