© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48593
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spot
    0.53
     part
    0.52
    ler
    0.52
     =
    0.51
     tuple
    0.50
     station
    0.50
     winner
    0.49
    I
    0.48
    R
    0.47
     tuples
    0.47
    POSITIVE LOGITS
    чков
    0.55
    тове
    0.54
    ม
    0.54
    𝘷
    0.54
     інте
    0.54
    щать
    0.53
    ٹو
    0.52
     хотела
    0.52
    ﻐ
    0.52
    ром
    0.52
    Activations Density 0.000%

    No Known Activations