© 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. 55039
    Prev
    Next
    INDEX
    Explanations

    will find, to mix, take

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

    foreign words or technical terms

    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
    Wool
    0.46
    Ply
    0.45
     แล
    0.45
     प्यारे
    0.45
    據
    0.44
    নি
    0.42
    Menus
    0.42
    夫婦
    0.42
    Secondo
    0.42
    Diana
    0.42
    POSITIVE LOGITS
     sampai
    0.52
     encontro
    0.47
    زمت
    0.47
    زش
    0.45
    WinCounter
    0.44
     aliquot
    0.44
     ṣ
    0.42
     totalidad
    0.42
     azúcar
    0.42
     anchoring
    0.42
    Activations Density 0.000%

    No Known Activations