© 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. 16-GEMMASCOPE-2-RES-16K
    7. 461
    Prev
    Next
    INDEX
    Explanations

    children invited

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

    Critical Role explanation

    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_16_width_16k_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
    t
    0.46
    A
    0.45
    ali
    0.44
    ä
    0.43
     A
    0.40
    r
    0.40
    í
    0.39
    á
    0.39
     It
    0.38
    rit
    0.38
    POSITIVE LOGITS
    も
    0.52
    ও
    0.48
    在
    0.43
    の
    0.39
    ᱕
    0.38
    ᱗
    0.38
     be
    0.37
    もら
    0.37
    도
    0.37
     době
    0.36
    Activations Density 3.764%

    No Known Activations