© 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. 142444
    Prev
    Next
    INDEX
    Explanations

    goods, possible, process, we, accurate

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

    valuable skills and effects

    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
     yanlış
    0.48
     prevención
    0.48
     வரவே
    0.47
     زيادة
    0.47
    .​​
    0.46
    스가
    0.46
     negativo
    0.46
     preparados
    0.46
     ወይም
    0.45
    attenzione
    0.45
    POSITIVE LOGITS
     arist
    0.47
    愔
    0.46
    使
    0.45
    中心
    0.43
    BASE
    0.42
    Emotion
    0.41
     empire
    0.41
     Bakufu
    0.41
    Ê
    0.41
     संघ
    0.41
    Activations Density 0.000%

    No Known Activations