© 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. 100621
    Prev
    Next
    INDEX
    Explanations

    lists or categories

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

    translation and linguistic concepts

    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
     Palermo
    0.47
    }{(
    0.45
    တိုင်း
    0.45
    xff
    0.44
     Pyrénées
    0.43
    VM
    0.43
     न्यायालय
    0.42
     burying
    0.42
     Philippines
    0.41
    ثمان
    0.41
    POSITIVE LOGITS
    滷
    0.49
    त्तीस
    0.48
    লিক
    0.47
     ஓர்
    0.47
    anlı
    0.47
     vissa
    0.46
     tolle
    0.45
    iatric
    0.45
     оформи
    0.45
    วัติ
    0.45
    Activations Density 0.000%

    No Known Activations