© 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. 70795
    Prev
    Next
    INDEX
    Explanations

    side by side

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

    non-English words and punctuation

    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
    ဗ
    0.43
     வாழை
    0.43
    \|_{
    0.42
     vườn
    0.42
     dislocations
    0.41
     இல்லை
    0.41
     \|_{
    0.41
    \|_{\
    0.40
     Juillet
    0.39
    ကုန်
    0.39
    POSITIVE LOGITS
     इसे
    0.44
     പ്രച
    0.44
    姗
    0.44
     इन्हें
    0.44
    恪
    0.43
     সংখ্যাল
    0.43
    ię
    0.42
     approfond
    0.42
    踽
    0.42
    tale
    0.41
    Activations Density 0.006%

    No Known Activations