© 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. 181219
    Prev
    Next
    INDEX
    Explanations

    George Stinney

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

    technical listings and analysis

    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
    広
    0.45
     evaded
    0.44
     enclave
    0.43
     paradigma
    0.41
     bici
    0.40
     marginalised
    0.40
    ᾧ
    0.40
     imidazole
    0.40
     dichotomy
    0.38
     ASGI
    0.38
    POSITIVE LOGITS
    PRODUCTION
    0.46
    骏
    0.44
    Morse
    0.44
     लड्डू
    0.44
    Dollars
    0.44
    Marshall
    0.42
     Sorrow
    0.42
    Dess
    0.41
    Mm
    0.41
    science
    0.41
    Activations Density 0.000%

    No Known Activations