© 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. 126015
    Prev
    Next
    INDEX
    Explanations

    game names

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

    deductive reasoning

    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
     escreveu
    0.53
    !”.
    0.47
    뇨
    0.46
    Ст
    0.46
     infar
    0.45
    ИА
    0.45
    粱
    0.45
    НГ
    0.45
     armazenamento
    0.44
    ຈັດສົ່ງ
    0.44
    POSITIVE LOGITS
    endant
    0.50
    ette
    0.49
    ville
    0.49
     kit
    0.48
     Jack
    0.47
     game
    0.46
     Damien
    0.46
     følgende
    0.46
     following
    0.45
     Game
    0.45
    Activations Density 0.001%

    No Known Activations