© 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. 225739
    Prev
    Next
    INDEX
    Explanations

    like this

    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
     ছাত্রী
    0.41
    bodyParser
    0.39
    onski
    0.39
     ইতোমধ্যে
    0.38
    oucester
    0.38
    addington
    0.37
     ಎಂದ
    0.36
     );
    0.36
    ieh
    0.35
     April
    0.35
    POSITIVE LOGITS
     подобные
    0.81
     подобных
    0.80
     இதுபோன்ற
    0.75
    このように
    0.75
     ఇలా
    0.68
     подоб
    0.66
    类似的
    0.66
     இதே
    0.65
     এরকম
    0.63
     similar
    0.61
    Activations Density 0.236%

    No Known Activations