© 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. 142862
    Prev
    Next
    INDEX
    Explanations

    crush, grill, cold, recommending

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

    your describing actions

    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
    ają
    0.48
    adri
    0.47
     henceforth
    0.46
    ależy
    0.46
    ąda
    0.45
     তত
    0.44
    olini
    0.44
     両
    0.44
     следует
    0.43
    Charter
    0.43
    POSITIVE LOGITS
     lepton
    0.56
    ﭘ
    0.49
     leuc
    0.46
    ்டு
    0.46
     nonconvex
    0.45
     лей
    0.45
     comical
    0.45
    ែ
    0.44
     tabel
    0.43
    marketing
    0.43
    Activations Density 0.000%

    No Known Activations