© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    mathematical and textual concepts

    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
     drain
    0.45
    또
    0.44
     pathways
    0.44
     público
    0.44
    ούν
    0.42
     transgression
    0.42
    drain
    0.42
    ğinin
    0.41
    ))]
    0.41
     announcements
    0.40
    POSITIVE LOGITS
     Choisissez
    0.54
     Couleur
    0.51
     caoutch
    0.50
     تجرب
    0.48
     poumon
    0.46
     ρ
    0.45
     كويس
    0.45
     لانه
    0.44
     plików
    0.44
     rougeâtre
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.