© 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-16K
    7. 12495
    Prev
    Next
    INDEX
    Explanations

    via your websites

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

    transformation, change, or state

    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_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
     b
    0.50
     hermaph
    0.49
     stunted
    0.49
     drifted
    0.49
     and
    0.48
     pitched
    0.47
     stable
    0.46
     surveyed
    0.45
     walnut
    0.45
    pos
    0.44
    POSITIVE LOGITS
     Announcement
    0.45
    に係る
    0.45
     ActivityCompat
    0.44
    rocessor
    0.43
    numericUpDown
    0.43
     ›
    0.42
    関数
    0.42
     істо
    0.42
     Activities
    0.42
    儀
    0.41
    Activations Density 0.003%

    No Known Activations