© 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. 766
    Prev
    Next
    INDEX
    Explanations

    instructions or questions

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

    geographic concentrationsingle suppliers

    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
     제한
    0.54
     فیصد
    0.52
     በጥ
    0.52
     facteurs
    0.50
     ຈ
    0.50
    ተው
    0.50
     ንጥረ
    0.49
     ఇతర
    0.49
     బల
    0.49
     ప్రస్తు
    0.48
    POSITIVE LOGITS
    }
    0.55
     Spor
    0.50
    логи
    0.49
     your
    0.49
     Garbage
    0.48
    رود
    0.47
    去
    0.46
     seh
    0.45
    Че
    0.44
     Enum
    0.44
    Activations Density 0.000%

    No Known Activations