© 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. 188337
    Prev
    Next
    INDEX
    Explanations

    type-specimen poster

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

    prized for value or exclusivity

    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
    侄
    0.54
    ərd
    0.47
    ਭ
    0.47
     réfrig
    0.47
    todolist
    0.46
    姪
    0.45
     rémun
    0.43
    老板
    0.43
    Actor
    0.41
    طلب
    0.41
    POSITIVE LOGITS
     Jahrhundert
    0.51
     Ras
    0.48
     culturale
    0.48
     クリーム
    0.46
     Ramp
    0.45
     Ondo
    0.45
     $_{
    0.45
     Layers
    0.45
     $_{\
    0.45
     layers
    0.44
    Activations Density 0.000%

    No Known Activations