© 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. 15543
    Prev
    Next
    INDEX
    Explanations

    take to scale

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

    follow instructions carefully

    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
     Kalman
    0.45
     Psy
    0.42
     Melton
    0.42
    👻
    0.42
     Nesta
    0.40
     Redmond
    0.40
     Beckett
    0.39
     Kim
    0.39
    —
    0.38
    妙
    0.38
    POSITIVE LOGITS
     estable
    0.43
     couvrir
    0.43
     breads
    0.41
     enceinte
    0.40
     mantiene
    0.40
     mapas
    0.40
     cuidar
    0.39
     rmg
    0.39
     regimens
    0.39
     facem
    0.39
    Activations Density 0.002%

    No Known Activations