© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10739
    Prev
    Next
    INDEX
    Explanations

    lie, lies, lied, ties, lieutenant

    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
    ---
    0.45
    to
    0.45
    sides
    0.45
    lodge
    0.44
    described
    0.43
    datas
    0.43
    Carry
    0.42
    trt
    0.42
    sigma
    0.42
    ство
    0.40
    POSITIVE LOGITS
    utenants
    0.55
     tie
    0.53
     lieb
    0.50
    utenant
    0.47
     છીએ
    0.47
     ties
    0.46
    谎
    0.45
     kie
    0.43
     LIE
    0.43
    तल
    0.42
    Activations Density 0.072%

    No Known Activations