© 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. 145700
    Prev
    Next
    INDEX
    Explanations

    language, synthesis, and thought processes

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

    foreign and 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
    उनकी
    0.52
    러스
    0.49
    евского
    0.49
    ului
    0.48
    🔞
    0.47
     ಅವರ
    0.47
    他們的
    0.46
    ILLE
    0.44
    울
    0.44
     వారి
    0.44
    POSITIVE LOGITS
     تكتب
    0.53
     scrivere
    0.52
     biosynthesis
    0.52
     photosynthesis
    0.50
     schreiben
    0.50
     synthesize
    0.49
     einfacher
    0.49
     संश्लेषण
    0.49
     pensar
    0.48
     pensée
    0.46
    Activations Density 0.000%

    No Known Activations