© 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. 184047
    Prev
    Next
    INDEX
    Explanations

    accumulated over, then have

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

    variable prefix and suffix

    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
    طلق
    0.48
    ي
    0.46
    قد
    0.43
     بسبب
    0.43
     والتي
    0.43
     rond
    0.40
     تقول
    0.40
     cancelar
    0.40
    ش
    0.40
    ادس
    0.39
    POSITIVE LOGITS
     বন্ধুত্ব
    0.52
    sphinx
    0.48
     diffeomorphism
    0.48
     ব্যবস্থাপনা
    0.47
    ଛି
    0.47
    ehr
    0.46
    {}".
    0.46
    ethe
    0.46
    ರಿನ
    0.45
    cuk
    0.45
    Activations Density 0.003%

    No Known Activations