© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11526
    Prev
    Next
    INDEX
    Explanations

    periods and exclamation marks

    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_40_width_16k_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
     divertida
    0.42
    forget
    0.42
    Honestly
    0.41
    紬
    0.41
    Seriously
    0.41
     creatividad
    0.41
    注意力
    0.41
    unless
    0.40
     escond
    0.40
     начну
    0.40
    POSITIVE LOGITS
     Produits
    0.39
     opponent
    0.39
    煒
    0.38
     derivation
    0.38
    etzten
    0.37
    DER
    0.37
    furnished
    0.36
     furnished
    0.36
     furnace
    0.36
     वर्तमान
    0.36
    Activations Density 0.048%

    No Known Activations