© 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. 117527
    Prev
    Next
    INDEX
    Explanations

    National Drink Wine Day

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

    stack web development

    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
    θηκε
    0.51
     دليل
    0.47
    變
    0.46
    曾經
    0.46
     ওয়াল
    0.44
     ديك
    0.44
     مس
    0.44
     abandoning
    0.43
     ಬದಲ
    0.43
     gelato
    0.43
    POSITIVE LOGITS
    ष्ठ
    0.41
    Treasurer
    0.41
    jectives
    0.40
     leptons
    0.40
    ก็
    0.40
    াভাব
    0.40
    직
    0.40
     क्यों
    0.39
    ्ले
    0.39
     फड
    0.39
    Activations Density 0.000%

    No Known Activations