© 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. 257210
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     tengah
    0.45
    oshi
    0.44
    yleg
    0.44
     book
    0.43
    ermin
    0.42
    S
    0.42
    4
    0.42
    gow
    0.42
    箐
    0.42
    ifer
    0.41
    POSITIVE LOGITS
     pretended
    0.49
    DanhMucSP
    0.48
     PRET
    0.46
    captured
    0.45
     pretends
    0.45
     prét
    0.45
    ږد
    0.45
     présentent
    0.45
     করল
    0.44
     transforme
    0.44
    Activations Density 0.000%

    No Known Activations