© 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. 123104
    Prev
    Next
    INDEX
    Explanations

    dental affinities

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

    id_rsa.pub, contrary, than

    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
    蚋
    0.58
    初期
    0.52
    運
    0.49
    載
    0.49
    ار
    0.49
    सारी
    0.48
    蓆
    0.48
    ليات
    0.46
    個人
    0.46
    Фото
    0.46
    POSITIVE LOGITS
     enthusiasm
    0.56
     엄
    0.48
     없
    0.47
     agreements
    0.47
     독
    0.47
     തോന്ന
    0.46
     을
    0.46
     effectiveness
    0.46
     horizontally
    0.46
     ऑर
    0.46
    Activations Density 0.001%

    No Known Activations