© 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. 5413
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite

    list of probabilities

    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
    ي
    0.64
    t
    0.57
    ت
    0.55
    i
    0.55
    خ
    0.52
    is
    0.51
    ان
    0.51
     Obsidian
    0.51
     premières
    0.50
     Optimal
    0.49
    POSITIVE LOGITS
     중심
    0.55
     тяж
    0.52
    大き
    0.51
     有限
    0.51
    阃
    0.51
     нагру
    0.50
     വിഷയ
    0.50
     yüzy
    0.50
    貸
    0.50
     зуб
    0.50
    Activations Density 0.000%

    No Known Activations