© 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. 208392
    Prev
    Next
    INDEX
    Explanations

    rates, savings, survey, clear

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

    adrenochrome, medical, therapeutic, paramagnetic, voltage

    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
     चपेट
    0.46
     naciones
    0.46
     incluidas
    0.45
     acciones
    0.44
    jangan
    0.44
    m
    0.43
    INCLUDE
    0.42
     کے
    0.42
    PACT
    0.41
    Bek
    0.41
    POSITIVE LOGITS
     trend
    0.47
     medical
    0.45
     laptop
    0.45
     salut
    0.44
     %``
    0.44
     cites
    0.43
     Neuro
    0.42
     DENUMIRE
    0.42
     paramagnetic
    0.42
     voltam
    0.42
    Activations Density 0.000%

    No Known Activations