© 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. 180734
    Prev
    Next
    INDEX
    Explanations

    successful cash saving

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

    communication channels, fluid retention, erosion control

    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
     ravaged
    0.44
     attacked
    0.43
     জানালেন
    0.43
    laboratory
    0.42
     laboratory
    0.42
     网
    0.41
     defeated
    0.40
    ﱠ
    0.40
     be
    0.40
    activité
    0.39
    POSITIVE LOGITS
    ウダー
    0.46
     estimés
    0.45
    हरू
    0.44
     ebben
    0.44
     पड़
    0.41
     советы
    0.41
     brunes
    0.40
     pekerja
    0.40
     Naik
    0.40
     Wail
    0.40
    Activations Density 0.001%

    No Known Activations