© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126173
    Prev
    Next
    INDEX
    Explanations

    paying for services and fees

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

    estimate Pi using circle

    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_31_width_262k_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
    世纪
    0.57
    水
    0.52
    风
    0.46
    太阳
    0.45
    发
    0.45
    拉
    0.45
     הר
    0.44
    列表
    0.42
    원
    0.42
    子
    0.42
    POSITIVE LOGITS
     regimens
    0.59
     Fresno
    0.59
    AWSJavaScriptSDK
    0.58
     Anaheim
    0.55
     countertops
    0.53
    নমেন্ট
    0.52
     Rohing
    0.52
     Mahomes
    0.52
     opposes
    0.51
    คองโก
    0.51
    Activations Density 0.001%

    No Known Activations