© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 74032
    Prev
    Next
    INDEX
    Explanations

    explanation of circumstances

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

    technical terms and definitions

    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
    鍘
    0.50
     baptized
    0.48
     коллек
    0.48
    镀
    0.46
    دأ
    0.44
     embro
    0.42
     Collections
    0.42
     caoutch
    0.42
    镟
    0.41
     پوکر
    0.41
    POSITIVE LOGITS
    これは
    0.50
    viving
    0.46
    жити
    0.46
     गैर
    0.45
    unpriv
    0.44
    이는
    0.44
    jiang
    0.44
    ront
    0.43
    それは
    0.43
    za
    0.43
    Activations Density 0.001%

    No Known Activations