© 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. 51695
    Prev
    Next
    INDEX
    Explanations

    attribution required or not

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

    attribution required

    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
     TRY
    0.49
     \
    0.43
    含有
    0.42
    l
    0.40
     स्टार्ट
    0.40
     각종
    0.40
     ಹಲವಾರು
    0.40
     ಈಗಾಗಲೇ
    0.39
     쭉
    0.39
     임
    0.39
    POSITIVE LOGITS
     heller
    0.41
     deviennent
    0.39
     méthode
    0.39
     pierres
    0.39
     പോലും
    0.38
     variabile
    0.38
    ەش
    0.37
    صفوف
    0.37
     amenaza
    0.37
     گیرد
    0.37
    Activations Density 0.000%

    No Known Activations