© 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. 27614
    Prev
    Next
    INDEX
    Explanations

    no obligation, to make, need for

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

    understanding how

    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
     n
    0.53
     f
    0.46
     hydrogen
    0.46
     minim
    0.46
     warehouse
    0.46
     i
    0.45
     u
    0.44
     creation
    0.44
     Util
    0.44
     reactor
    0.43
    POSITIVE LOGITS
     выбрать
    0.56
     wybrać
    0.53
     प्रशिक्षित
    0.53
    י
    0.53
     งวด
    0.52
    𒁾
    0.52
    لڈ
    0.51
    嚗
    0.51
    <unused48>
    0.50
     পর্যায়ের
    0.50
    Activations Density 0.000%

    No Known Activations