© 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. 62684
    Prev
    Next
    INDEX
    Explanations

    bring to the table each time

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

    what has changed

    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
    F
    0.48
    Medical
    0.44
    withdrawal
    0.44
     Limitations
    0.44
    Miche
    0.43
    但不
    0.43
    hi
    0.43
    S
    0.42
    T
    0.41
    U
    0.41
    POSITIVE LOGITS
     gameplay
    0.51
     showdown
    0.51
     lexicon
    0.49
     postings
    0.49
     জিজ্ঞাসা
    0.48
     boutiques
    0.48
     mobile
    0.47
     raindrops
    0.47
     buoy
    0.47
     hydrological
    0.47
    Activations Density 0.000%

    No Known Activations