© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 204423
    Prev
    Next
    INDEX
    Explanations

    link in code

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

    creative writing prompts

    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
    ွေ
    0.47
    ないので
    0.46
     validity
    0.45
    ূন্য
    0.44
     _
    0.43
     flavor
    0.43
    uí
    0.43
     dever
    0.43
    ật
    0.43
     congreg
    0.43
    POSITIVE LOGITS
    leştir
    0.58
    </strong>
    0.50
     অভিন
    0.49
    ה
    0.49
     خار
    0.48
    Playing
    0.48
    籶
    0.47
    father
    0.46
    Yves
    0.46
     स्ने
    0.45
    Activations Density 0.000%

    No Known Activations