© 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. 132751
    Prev
    Next
    INDEX
    Explanations

    completed, destroyed, closing, following, ever

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

    brief descriptions or prompts

    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
    撹
    0.48
    て
    0.48
    ᔾ
    0.46
     ostensibly
    0.44
    မ့်
    0.44
    ᒧ
    0.44
    的确
    0.43
    տ
    0.43
     verses
    0.43
    ırd
    0.43
    POSITIVE LOGITS
    ienti
    0.46
    anny
    0.45
    ien
    0.44
    ilian
    0.43
    anson
    0.43
    olus
    0.42
     امام
    0.41
     вони
    0.41
    onet
    0.41
     पादुकोण
    0.41
    Activations Density 0.000%

    No Known Activations