© 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. 74832
    Prev
    Next
    INDEX
    Explanations

    anywhere away win

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

    Toronto to name

    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
     блок
    0.50
    在这种
    0.47
     simplic
    0.46
     класс
    0.43
     правой
    0.43
    мин
    0.43
    纡
    0.43
    硗
    0.43
     Economía
    0.42
    OfWeek
    0.42
    POSITIVE LOGITS
     memiliki
    0.49
    stem
    0.49
     identifies
    0.47
     to
    0.47
     tennis
    0.47
    इजेशन
    0.47
    1
    0.46
     takes
    0.45
     dubbed
    0.44
    ukh
    0.44
    Activations Density 0.004%

    No Known Activations