© 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. 27793
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

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

    Jira Cloud, PDF parsing, API

    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
     uninsured
    0.60
     Masonic
    0.45
     compradores
    0.44
     H
    0.42
     aliados
    0.42
     Marcos
    0.41
     mengambil
    0.41
     insured
    0.41
     estimados
    0.41
     hombres
    0.41
    POSITIVE LOGITS
     Zeitschrift
    0.46
    矍
    0.44
    変化
    0.42
     Archiv
    0.42
    ヨーロッパ
    0.42
    ግኘት
    0.42
     యొక్క
    0.41
     archiv
    0.41
     கண்க
    0.40
    Gesch
    0.39
    Activations Density 0.000%

    No Known Activations