© 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. 22740
    Prev
    Next
    INDEX
    Explanations

    will find, associated with

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

    slow blink conveyed meaning

    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
     rotational
    0.48
     armament
    0.46
     modulus
    0.44
    (
    0.44
     vasculature
    0.43
     metabolism
    0.42
     adverts
    0.41
     fluoro
    0.40
    0.40
    c
    0.40
    POSITIVE LOGITS
    фі
    0.51
    एस्ट
    0.51
    অগ্র
    0.51
    🄴
    0.49
    러스
    0.48
    берите
    0.47
     Вайлд
    0.47
     найкра
    0.47
    мся
    0.47
    تقديم
    0.47
    Activations Density 0.000%

    No Known Activations