© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107310
    Prev
    Next
    INDEX
    Explanations

    cannot or can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рим
    -0.88
    ETZ
    -0.84
    ходили
    -0.78
    ėk
    -0.77
    えば
    -0.77
    <0x17>
    -0.77
     أهم
    -0.76
    ந
    -0.76
    агностика
    -0.76
    ведь
    -0.76
    POSITIVE LOGITS
     cannot
    7.88
    Cannot
    5.09
    cannot
    5.09
     Cannot
    5.00
     нельзя
    4.16
     CANNOT
    3.72
    不能
    3.61
     can
    3.06
    无法
    2.92
    無法
    2.86
    Activations Density 0.224%

    No Known Activations