© 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. 148847
    Prev
    Next
    INDEX
    Explanations

    purposes, phones, security, elegant style

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

    indie game

    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
    ਭ
    0.46
     яко
    0.43
    𝖚
    0.43
     europé
    0.42
     верх
    0.42
     verwij
    0.42
     обрабаты
    0.42
    凍
    0.42
     γά
    0.42
    錨
    0.42
    POSITIVE LOGITS
    andes
    0.51
     அல்லது
    0.47
    栉
    0.46
    どうしても
    0.45
    ہوں
    0.44
    usions
    0.43
    zony
    0.43
     لمدة
    0.43
     सिसोदिया
    0.43
    ه‌های
    0.43
    Activations Density 0.000%

    No Known Activations