© 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. 44943
    Prev
    Next
    INDEX
    Explanations

    it is/always/never

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

    classic, but effective

    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
     этих
    0.50
    嵃
    0.50
     这些
    0.47
     цих
    0.47
    єї
    0.46
     Например
    0.46
    这些
    0.46
    比如说
    0.45
    比如說
    0.45
    贍
    0.45
    POSITIVE LOGITS
     used
    0.58
     precursor
    0.52
     usado
    0.49
     headquartered
    0.48
     incorporates
    0.48
     utilizado
    0.48
     utilisée
    0.47
     debuted
    0.47
     utilisé
    0.46
     specialises
    0.46
    Activations Density 0.074%

    No Known Activations