© 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. 257523
    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
     लिंक
    0.51
    ॅप
    0.50
     देण्यासाठी
    0.48
    }:=
    0.46
    rom
    0.46
    ラの
    0.45
    เท
    0.45
    aping
    0.45
    াতাড়ি
    0.45
    竰
    0.44
    POSITIVE LOGITS
     woes
    0.47
     helpers
    0.47
     cages
    0.46
     hues
    0.44
     adapters
    0.44
     fittings
    0.43
     shrines
    0.43
     était
    0.43
     WAS
    0.42
     empê
    0.41
    Activations Density 0.000%

    No Known Activations