© 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. 255357
    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
    ಂತೆ
    0.56
    颛
    0.53
    tı
    0.52
    <0xEC>
    0.51
    리
    0.50
    岩
    0.50
    傥
    0.49
    <0xED>
    0.49
    яр
    0.48
    느
    0.48
    POSITIVE LOGITS
    orca
    0.50
    licken
    0.47
    olla
    0.47
    ings
    0.45
    onn
    0.44
    ngen
    0.44
    comics
    0.44
     noten
    0.44
    batross
    0.44
    polar
    0.44
    Activations Density 0.001%

    No Known Activations