© 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-262K
    7. 34285
    Prev
    Next
    INDEX
    Explanations

    code structure inspection

    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
    venv
    0.38
    Maven
    0.38
    pom
    0.37
    nltk
    0.37
    __:
    0.37
    γωγ
    0.36
    <<"\
    0.35
    력을
    0.35
    Gradle
    0.34
    mények
    0.34
    POSITIVE LOGITS
     inspection
    0.66
     Inspection
    0.64
    Inspection
    0.64
     inspections
    0.60
    inspection
    0.56
     inspect
    0.54
     inspecting
    0.54
     Inspe
    0.53
     inspector
    0.52
     inspectors
    0.51
    Activations Density 0.001%

    No Known Activations