© 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. 44818
    Prev
    Next
    INDEX
    Explanations

    Indian army

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

    Indian phrases

    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
     keySchedule
    0.45
    Elater
    0.43
    LensFlare
    0.42
     médian
    0.42
    зец
    0.42
    FlowNode
    0.41
    Ƒ
    0.41
    对话
    0.41
     Observing
    0.41
    وینت
    0.40
    POSITIVE LOGITS
     Bollywood
    0.63
     Chandigarh
    0.56
     Delhi
    0.54
     Maharaja
    0.54
     bhai
    0.54
     Bhajan
    0.53
     Bharat
    0.51
     Jammu
    0.51
     bollywood
    0.50
     Paytm
    0.49
    Activations Density 0.001%

    No Known Activations