© 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. 251155
    Prev
    Next
    INDEX
    Explanations

    pt. 2

    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
     书
    0.55
     clashes
    0.54
     库存
    0.53
     云
    0.52
     LDGs
    0.52
     ましょう
    0.51
     圆
    0.50
     Alright
    0.50
    সঙ্ঘ
    0.50
     克
    0.50
    POSITIVE LOGITS
    ap
    0.68
    b
    0.55
    м
    0.55
    リ
    0.54
    ph
    0.53
    pt
    0.52
    que
    0.51
    ooo
    0.50
    onas
    0.50
    oo
    0.49
    Activations Density 0.000%

    No Known Activations