© 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. 31951
    Prev
    Next
    INDEX
    Explanations

    sentence start context

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

    making you think

    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
    </h3>
    0.43
    swürdig
    0.41
     सेलिब्र
    0.41
    !!");
    0.41
     عط
    0.40
    国の
    0.40
    竟
    0.40
    !!!");
    0.40
    !");
    0.39
     पिक्च
    0.39
    POSITIVE LOGITS
     broad
    0.46
     receding
    0.46
     peneliti
    0.46
     advances
    0.45
     grounding
    0.45
     intéressante
    0.45
     proximal
    0.45
     platforms
    0.45
     rural
    0.44
     ترکیب
    0.44
    Activations Density 0.000%

    No Known Activations