© 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. 174114
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    updated, calm, Ah, elevates, bleach, supplements, arms

    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
     наша
    0.47
     તમારા
    0.47
     вече
    0.47
     महंगा
    0.46
     ваша
    0.46
     ваш
    0.46
     ե
    0.44
    慟
    0.44
     તેના
    0.44
     www
    0.43
    POSITIVE LOGITS
    _
    0.55
    كان
    0.51
    measurement
    0.47
    measurable
    0.46
     expropri
    0.46
    ازی
    0.45
    from
    0.43
     necessitate
    0.43
    پ
    0.43
    ¿
    0.43
    Activations Density 0.000%

    No Known Activations