© 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. 7014
    Prev
    Next
    INDEX
    Explanations

    shapes sizes orth pred getting

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

    whisper, range, Fold, Pembrolizumab

    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
     الفيديو
    0.50
    innitus
    0.47
    視頻
    0.47
     వీడియో
    0.46
    ябре
    0.45
    캔
    0.44
     celebratory
    0.44
     ದೊಡ್ಡ
    0.44
    हमारी
    0.43
    retanto
    0.43
    POSITIVE LOGITS
     costes
    0.57
     asesin
    0.53
     geht
    0.52
     schme
    0.51
     biens
    0.50
     ints
    0.48
     ansch
    0.48
     quels
    0.48
    <0xA9>
    0.46
     svar
    0.46
    Activations Density 0.000%

    No Known Activations