© 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. 145251
    Prev
    Next
    INDEX
    Explanations

    BMW 3, double beds, programs administered

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

    don't fit or fix

    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
    eced
    0.49
    itação
    0.48
     calculado
    0.48
    <0x93>
    0.46
    橇
    0.46
    datos
    0.46
    han
    0.45
    halter
    0.45
    polished
    0.45
    ati
    0.45
    POSITIVE LOGITS
     एयर
    0.46
    ？？
    0.46
    押
    0.46
    通り
    0.45
     ४
    0.45
     Sem
    0.44
     Agar
    0.44
    方形
    0.44
     ஏற்படுத்துகிறது
    0.44
    お客
    0.44
    Activations Density 0.001%

    No Known Activations