© 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. 11116
    Prev
    Next
    INDEX
    Explanations

    numbers and types of things

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

    statistical terms

    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
    er
    0.79
    in
    0.58
    f
    0.55
    al
    0.53
    ate
    0.53
    te
    0.53
    u
    0.52
    ar
    0.50
    gol
    0.50
    it
    0.49
    POSITIVE LOGITS
     personnes
    0.60
     harnessed
    0.57
     edilir
    0.55
     procesu
    0.55
     rodzaju
    0.54
     cancé
    0.53
     ziek
    0.52
     bacterias
    0.51
     construed
    0.51
     uczni
    0.50
    Activations Density 0.000%

    No Known Activations