© 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. 55720
    Prev
    Next
    INDEX
    Explanations

    following lists

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

    or black

    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
    ணி
    0.48
    いている
    0.48
    臀
    0.47
     vasodil
    0.46
    夏の
    0.46
    ânica
    0.45
    церт
    0.45
     químicos
    0.45
    وید
    0.45
     verildi
    0.44
    POSITIVE LOGITS
    chips
    0.46
     ಕೂ
    0.45
    dp
    0.43
     Crus
    0.43
    এই
    0.42
    iany
    0.42
     we
    0.42
    0
    0.42
     Kol
    0.40
     stats
    0.40
    Activations Density 0.000%

    No Known Activations