© 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. 132217
    Prev
    Next
    INDEX
    Explanations

    Jewish jams daughter frustrations Americans suburban

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

    effects after friction

    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
    가의
    0.48
    proses
    0.48
     традиции
    0.48
    FRONT
    0.46
    This
    0.46
    sites
    0.45
    ссы
    0.45
    𝕡
    0.45
    นะนำ
    0.45
    sounds
    0.45
    POSITIVE LOGITS
     famílias
    0.56
     malnourished
    0.52
     worsen
    0.50
     pacientes
    0.49
     ಪಕ್ಷ
    0.49
     vendeurs
    0.49
     patients
    0.48
     worsened
    0.48
     imbalance
    0.47
     なっ
    0.46
    Activations Density 0.000%

    No Known Activations