© 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. 210780
    Prev
    Next
    INDEX
    Explanations

    deputy directors

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

    introduces explanations or definitions

    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
    bieter
    0.48
    omyel
    0.47
     सुबह
    0.46
    toare
    0.45
    ★★
    0.44
     প্রতিদিনই
    0.44
    adil
    0.43
    JEE
    0.43
     ቀን
    0.43
     ลด
    0.43
    POSITIVE LOGITS
     sanded
    0.48
     دیکھا
    0.46
     sandstone
    0.46
     branding
    0.45
     gratitude
    0.43
     Rally
    0.42
    ن
    0.42
     sanding
    0.42
    َف
    0.41
    цам
    0.41
    Activations Density 0.003%

    No Known Activations