© 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. 16613
    Prev
    Next
    INDEX
    Explanations

    encouraged to, not, created through

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

    commercial use, potential trend, merges

    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
    ה
    0.52
     fortress
    0.45
     сахар
    0.45
    צא
    0.44
     που
    0.42
     страны
    0.42
    ként
    0.42
     이름
    0.42
    ש
    0.42
     שה
    0.41
    POSITIVE LOGITS
    五个
    0.43
    Primo
    0.43
    TP
    0.42
    Topo
    0.42
     Floyd
    0.42
     Primo
    0.42
    eredith
    0.41
     Doyle
    0.41
     EY
    0.40
    Simpson
    0.40
    Activations Density 0.000%

    No Known Activations