© 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. 64011
    Prev
    Next
    INDEX
    Explanations

    descriptions following common words

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

    Activities overview

    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
    lassen
    0.54
     komplex
    0.53
     modular
    0.50
     delusions
    0.49
    £
    0.48
     hammer
    0.48
     demons
    0.48
     priorities
    0.47
     guru
    0.47
     inescap
    0.47
    POSITIVE LOGITS
    𝚄
    0.47
    提交
    0.46
    上传
    0.46
    夻
    0.44
    อรี่
    0.44
    🆗
    0.44
    不论
    0.43
     ενη
    0.43
     ресу
    0.43
    顺利
    0.42
    Activations Density 0.000%

    No Known Activations