© 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. 236064
    Prev
    Next
    INDEX
    Explanations

    major international

    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
     alimentação
    0.55
    剂量
    0.52
    槅
    0.52
     ავ
    0.51
    öffentlichung
    0.50
     bedrijf
    0.50
    途径
    0.49
    يت
    0.49
     原因
    0.49
     يأ
    0.49
    POSITIVE LOGITS
    RR
    0.52
    Colombo
    0.49
    S
    0.49
    Ci
    0.48
    Y
    0.48
    F
    0.47
     TES
    0.46
    K
    0.46
    R
    0.46
    TES
    0.44
    Activations Density 0.000%

    No Known Activations