© 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. 251704
    Prev
    Next
    INDEX
    Explanations

    important, USB, did, execution

    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
     گر
    0.49
    ppes
    0.45
     diad
    0.44
    ޑ
    0.44
     $=\
    0.44
     ایڈ
    0.43
    mathfrak
    0.42
     separable
    0.42
     nath
    0.42
     Econom
    0.42
    POSITIVE LOGITS
    ết
    0.48
    现在
    0.45
    资金
    0.43
    强化
    0.43
    恐惧
    0.41
    统
    0.41
    捆
    0.41
    强
    0.41
     quỹ
    0.40
     Machines
    0.40
    Activations Density 0.001%

    No Known Activations