© 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. 169425
    Prev
    Next
    INDEX
    Explanations

    SCHEDULE A hereto

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

    shaping or reshaping the future

    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
    으로서
    0.48
    û
    0.47
    î
    0.47
     загру
    0.46
    irlas
    0.46
    íd
    0.44
    ה
    0.44
    êng
    0.43
    筋肉
    0.43
    о
    0.43
    POSITIVE LOGITS
     attendance
    0.49
     organization
    0.49
     outpatient
    0.49
     보자
    0.48
     sentences
    0.46
     packet
    0.46
     byte
    0.46
     liu
    0.46
     openai
    0.45
    وانات
    0.44
    Activations Density 0.002%

    No Known Activations