© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102869
    Prev
    Next
    INDEX
    Explanations

    full potential, talent level, extreme environments

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

    self-analyzing actions or states

    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
    Negative Logits
    ר
    0.51
    hwar
    0.48
     OBE
    0.46
     aden
    0.46
    CRUD
    0.46
    視
    0.45
    爲
    0.44
    uß
    0.44
    спользование
    0.43
    SNR
    0.43
    POSITIVE LOGITS
     größten
    0.47
     সবগুলো
    0.47
    )..
    0.46
     polov
    0.46
     сезон
    0.46
     "../
    0.44
     próximo
    0.44
     plur
    0.44
    地區
    0.44
     سعيد
    0.43
    Activations Density 0.001%

    No Known Activations