© 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. 3612
    Prev
    Next
    INDEX
    Explanations

    function documentation returns

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

    function return values

    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
     христиан
    0.50
     আমায়
    0.49
    醣
    0.49
    avacanam
    0.48
     বসিয়া
    0.47
     গিয়াছেন
    0.47
     христи
    0.47
    thisTrack
    0.47
    ヨーク
    0.47
    糖尿
    0.47
    POSITIVE LOGITS
     {@
    1.02
    {@
    0.69
     optionally
    0.68
     accessor
    0.66
     deserial
    0.65
     specifies
    0.63
     Returns
    0.63
     identifies
    0.63
     initializes
    0.62
    返回
    0.61
    Activations Density 0.049%

    No Known Activations