© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    numbers with decimal points

    np_acts-logits-general · gemini-2.5-flash-lite

    starts or ends at zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    拿着
    0.44
    ખ્યા
    0.43
     லட்ச
    0.40
     वेलकम
    0.40
    ಕ್ಸ್
    0.40
     अवैध
    0.40
    Сто
    0.40
    琕
    0.40
     lak
    0.40
    第五
    0.40
    POSITIVE LOGITS
    ponen
    0.41
     Venez
    0.40
     IMA
    0.40
    とし
    0.37
    udin
    0.37
    륜
    0.37
     Corresponding
    0.36
     sfor
    0.36
    вна
    0.36
    にします
    0.35
    Activations Density 0.014%

    No Known Activations