© 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. 124835
    Prev
    Next
    INDEX
    Explanations

    definitions and questions

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

    Anki and harm mitigation

    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
     harvests
    0.44
     প্রতিটি
    0.43
     Puoi
    0.43
     silky
    0.43
    🍂
    0.43
     fluoro
    0.42
     repurposed
    0.42
    唷
    0.41
     velvety
    0.40
     повністю
    0.40
    POSITIVE LOGITS
     सहानुभूति
    0.45
    engel
    0.43
    ffekt
    0.40
    ంద
    0.39
    мен
    0.39
    ennen
    0.39
    อด
    0.38
     Ant
    0.37
    ลก
    0.37
    ften
    0.37
    Activations Density 0.000%

    No Known Activations