© 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. 39506
    Prev
    Next
    INDEX
    Explanations

    invented, developed, or devised

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

    negation and conceptual 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
    不上
    0.48
    쫒
    0.46
     हमारे
    0.46
    调节
    0.46
    性
    0.44
     प्रभारी
    0.44
    লা
    0.43
    毎日
    0.43
     আগুন
    0.42
    劳
    0.42
    POSITIVE LOGITS
     syntax
    0.52
     grammat
    0.52
     hypothesized
    0.52
     conceptually
    0.52
     notation
    0.50
     multilingual
    0.50
     algebraic
    0.50
     describing
    0.50
     languages
    0.49
     conjectured
    0.47
    Activations Density 0.000%

    No Known Activations