© 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. 61200
    Prev
    Next
    INDEX
    Explanations

    common phrases and specifications

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

    ** is a list item indicator

    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
    ي
    0.55
    prepareStatement
    0.51
    Ticks
    0.51
    主要的
    0.51
    본
    0.50
    شهر
    0.49
    annya
    0.48
    te
    0.46
    ن
    0.46
    परि
    0.46
    POSITIVE LOGITS
     ол
    0.56
     odor
    0.52
     misuse
    0.52
     produits
    0.51
     odors
    0.50
     имуще
    0.50
     products
    0.49
     harmonization
    0.49
     RED
    0.49
     り
    0.48
    Activations Density 0.000%

    No Known Activations