© 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. 42197
    Prev
    Next
    INDEX
    Explanations

    numbers and slashes

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

    recipe structure or sentence fragment

    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
     bm
    0.45
    ={(
    0.44
     counties
    0.43
     会
    0.43
    n
    0.42
     DE
    0.42
     local
    0.41
     mineral
    0.41
     ={
    0.41
     townships
    0.41
    POSITIVE LOGITS
    zado
    0.52
    شتی
    0.50
    ceaux
    0.46
     کھیلتے
    0.45
    żliw
    0.45
    ốn
    0.45
    ća
    0.44
    ować
    0.44
     esemplari
    0.44
     ہتھیار
    0.44
    Activations Density 0.000%

    No Known Activations