© 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-65K
    7. 55566
    Prev
    Next
    INDEX
    Explanations

    OF followed by words like froth or offers

    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_65k_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
    𒂍
    0.42
    elé
    0.40
    Ole
    0.39
    뢨
    0.38
    ounter
    0.38
     Adrien
    0.37
    ysk
    0.37
    耔
    0.37
     aeron
    0.37
    hek
    0.36
    POSITIVE LOGITS
     froth
    0.44
     ofrece
    0.39
    ENSITY
    0.39
    <end_of_turn>
    0.38
     leveled
    0.38
     nourished
    0.38
     offers
    0.38
     OF
    0.38
     zenith
    0.37
     оформ
    0.37
    Activations Density 0.010%

    No Known Activations