© 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. 40301
    Prev
    Next
    INDEX
    Explanations

    according to

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

    analytical responses, compartmental structure

    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
    ình
    0.53
    пот
    0.51
    峽
    0.49
    ш
    0.47
     unseren
    0.46
     nasz
    0.46
     наш
    0.46
     teníamos
    0.45
     нашу
    0.44
    我們會
    0.44
    POSITIVE LOGITS
     frustration
    0.47
     frustrating
    0.47
     frust
    0.45
     frustrated
    0.45
     カラ
    0.44
     dx
    0.43
     Poisson
    0.43
    )
    0.42
    du
    0.42
     stop
    0.42
    Activations Density 0.000%

    No Known Activations