© 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. 233079
    Prev
    Next
    INDEX
    Explanations

    leading aluminum extrusion producer

    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
     球
    0.49
     lentes
    0.47
     egress
    0.47
     RTR
    0.46
     lập
    0.46
     Atr
    0.46
     STA
    0.45
     portato
    0.45
     alej
    0.45
     pendientes
    0.45
    POSITIVE LOGITS
    on
    0.48
    در
    0.46
    ست
    0.45
    acknow
    0.45
    在
    0.45
    ंमध्ये
    0.43
    డ్డ
    0.43
    obl
    0.43
    olith
    0.43
    चर्स
    0.42
    Activations Density 0.000%

    No Known Activations