© 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. 88911
    Prev
    Next
    INDEX
    Explanations

    Palacio Nacional, Eightfold, polycythemia, typo

    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
    È
    0.51
     to
    0.48
    É
    0.47
    C
    0.47
    Есть
    0.46
    िट
    0.46
    Á
    0.46
    ต้อง
    0.45
    Arc
    0.45
    LLY
    0.45
    POSITIVE LOGITS
     fluidity
    0.51
    iedades
    0.50
     prologue
    0.50
     ល
    0.49
    ncies
    0.48
     cleaved
    0.48
    尿
    0.48
    druck
    0.48
     hordes
    0.48
    naires
    0.48
    Activations Density 0.000%

    No Known Activations