© 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. 13013
    Prev
    Next
    INDEX
    Explanations

    pre- prefix

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

    pre- prefix

    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
     It
    0.70
    a
    0.66
    া
    0.63
    ור
    0.60
    ری
    0.58
     internas
    0.57
    ા
    0.57
     instala
    0.56
    קי
    0.54
     powied
    0.54
    POSITIVE LOGITS
     pre
    1.37
     प्री
    1.28
    pre
    1.23
     пре
    1.17
    Pre
    1.11
     Pre
    1.10
    预
    1.05
     pré
    1.02
    預
    0.91
     ప్రీ
    0.89
    Activations Density 0.055%

    No Known Activations