© 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. 165611
    Prev
    Next
    INDEX
    Explanations

    electronic/future

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

    potential signaling

    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
    경
    0.49
    msg
    0.47
    알
    0.46
    신
    0.45
    nau
    0.45
     premed
    0.45
    玛
    0.45
    パイ
    0.43
    매
    0.43
    Papa
    0.43
    POSITIVE LOGITS
     Electronic
    0.52
    的可能性
    0.51
    𒌉
    0.51
     электрон
    0.50
     इलेक्ट्रॉनिक
    0.50
     ηλεκ
    0.50
    electronic
    0.49
     ইউজ
    0.49
     同じ
    0.49
     ポイント
    0.49
    Activations Density 0.000%

    No Known Activations