© 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. 86822
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

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

    Stateful followed by deployment or state description

    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
     প্র
    0.51
     thaliana
    0.49
     generate
    0.48
    ：
    0.47
    ，
    0.46
     generated
    0.46
     Nottingham
    0.46
     K
    0.45
    .”
    0.45
    ↵↵
    0.44
    POSITIVE LOGITS
    ೦
    0.50
     excepciones
    0.50
    čnom
    0.50
    odin
    0.49
    ados
    0.48
    lawful
    0.48
     declaraciones
    0.48
    informations
    0.48
     उपर
    0.48
    אם
    0.47
    Activations Density 0.001%

    No Known Activations