© 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. 154429
    Prev
    Next
    INDEX
    Explanations

    given error

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

    predicting 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
     naps
    0.48
     পরবর্তীতে
    0.47
     داعش
    0.45
    ^{\#}\
    0.45
     dibuj
    0.44
     rupt
    0.44
     robberies
    0.43
    !!!");
    0.43
     crevices
    0.43
    最后一个
    0.43
    POSITIVE LOGITS
     Insulation
    0.48
    两大
    0.42
     unica
    0.41
    の方法
    0.40
     bergantung
    0.40
     ప్రకారం
    0.39
    筚
    0.39
    ല്
    0.38
     অবশ্য
    0.38
     appeal
    0.38
    Activations Density 0.001%

    No Known Activations