© 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-262K
    7. 1573
    Prev
    Next
    INDEX
    Explanations

    National Sexual Assault Hotline

    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_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
    julia
    0.30
    ref
    0.30
    A
    0.29
    Description
    0.28
    [](
    0.28
    reflected
    0.27
    Ref
    0.27
    work
    0.27
    result
    0.27
    拟
    0.27
    POSITIVE LOGITS
     નીચે
    0.30
     নাম্বার
    0.30
     ниже
    0.29
     admires
    0.29
     Wach
    0.29
     undead
    0.29
     admire
    0.28
     impuls
    0.28
     impulso
    0.28
     impot
    0.28
    Activations Density 0.021%

    No Known Activations