© 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. 124808
    Prev
    Next
    INDEX
    Explanations

    publicly available sources

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

    reducing support, manual effort

    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
    富有
    0.49
     MÉ
    0.46
    troop
    0.46
    庸
    0.46
    ḳ
    0.46
     बॉस
    0.45
     WORTH
    0.45
    йл
    0.45
    పర్
    0.44
    K
    0.44
    POSITIVE LOGITS
     allegedly
    0.49
     )
    0.48
    ense
    0.47
     stages
    0.47
    ensing
    0.46
     this
    0.46
     supposedly
    0.46
     apparently
    0.45
     {
    0.45
     hardening
    0.45
    Activations Density 0.001%

    No Known Activations