© 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. 41-GEMMASCOPE-2-RES-262K
    7. 59212
    Prev
    Next
    INDEX
    Explanations

    macros `#define`

    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_all/layer_41_width_262k_l0_big
    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
    諧
    0.41
    ARIA
    0.40
    ̸
    0.40
    %);
    0.39
     turpentine
    0.38
     brillant
    0.38
     anise
    0.38
    ='$
    0.38
    ziger
    0.38
    тус
    0.37
    POSITIVE LOGITS
    if
    0.44
     कुशल
    0.39
     ដែល
    0.38
     privaten
    0.38
    ech
    0.38
     Guerre
    0.37
    rano
    0.36
    qués
    0.36
     hoạch
    0.36
    oods
    0.36
    Activations Density 0.000%

    No Known Activations