© 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. 247458
    Prev
    Next
    INDEX
    Explanations

    inside or outside dimensions

    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
     ك
    0.52
     biskup
    0.46
    酒吧
    0.45
    翻译
    0.45
     الجيش
    0.45
    侪
    0.44
     olas
    0.44
     sogar
    0.42
     جديدة
    0.42
    Kayak
    0.41
    POSITIVE LOGITS
    ного
    0.48
    entric
    0.47
    α
    0.44
    mete
    0.43
    netics
    0.43
    フィ
    0.42
    ability
    0.42
    メタ
    0.42
    સો
    0.41
    Gr
    0.41
    Activations Density 0.001%

    No Known Activations