© 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. 55402
    Prev
    Next
    INDEX
    Explanations

    then, if, and then

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

    logarithm base and units

    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
     instagram
    0.42
     />
    0.41
    ö
    0.40
     suc
    0.40
    ɡ
    0.39
    jar
    0.38
    Ї
    0.38
    github
    0.38
    aws
    0.38
    पूर्व
    0.38
    POSITIVE LOGITS
     Aufnahme
    0.51
    扭
    0.50
     akzept
    0.50
    kta
    0.49
     Studien
    0.48
    ielles
    0.47
     Kapitel
    0.46
     Ausgabe
    0.45
     Variablen
    0.44
     racine
    0.44
    Activations Density 0.001%

    No Known Activations