© 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. 68582
    Prev
    Next
    INDEX
    Explanations

    what does it mean

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

    notify Controller

    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
    define
    0.51
    defining
    0.50
    𝐑
    0.46
    Defining
    0.46
    障害
    0.44
    يف
    0.43
     Firstly
    0.43
    逢
    0.43
     دنی
    0.43
    мян
    0.42
    POSITIVE LOGITS
     muttered
    0.46
     murmured
    0.46
     régler
    0.43
    ቸው
    0.42
     übrig
    0.41
     niece
    0.41
     zebrafish
    0.41
     Isso
    0.40
    embourg
    0.40
     walter
    0.40
    Activations Density 0.000%

    No Known Activations