© 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. 3821
    Prev
    Next
    INDEX
    Explanations

    organizations and events

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

    Important sections and resources

    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
    𝔪
    0.32
    motionProxy
    0.31
     צריך
    0.29
    வ்வேறு
    0.29
     estran
    0.28
    データを
    0.27
     mauvaise
    0.27
     ಸಮಸ್ಯೆ
    0.27
    itriangular
    0.27
     spectrometers
    0.27
    POSITIVE LOGITS
     Toolkit
    0.47
     Guide
    0.46
     Workshop
    0.40
     Initiative
    0.39
    ™
    0.39
     &
    0.38
     II
    0.37
     Series
    0.37
     Suite
    0.36
     Seminar
    0.35
    Activations Density 0.989%

    No Known Activations