© 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. 30298
    Prev
    Next
    INDEX
    Explanations

    phrases related to days and actions

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

    Predicts next bar's, inevitable arguments, available width

    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
     договора
    0.51
     bookArray
    0.50
    ಿಯೂ
    0.46
    কমার
    0.45
    ското
    0.45
    व्यवस्था
    0.45
    ও
    0.44
    配套
    0.43
    なければ
    0.43
    ativen
    0.43
    POSITIVE LOGITS
     Pawn
    0.48
    herb
    0.46
     Branco
    0.45
     podemos
    0.44
     तुम्ही
    0.43
     limitado
    0.42
     puedes
    0.41
     podríamos
    0.41
     பரிந்து
    0.41
     Herb
    0.41
    Activations Density 0.000%

    No Known Activations