© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4446
    Prev
    Next
    INDEX
    Explanations

    programming terms and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elektrokh
    0.35
     thoracique
    0.34
    طه
    0.32
     thérapeut
    0.31
     zvyš
    0.30
    脓
    0.29
     cotid
    0.29
    🥅
    0.29
    猞
    0.29
     नाइट्रोजन
    0.29
    POSITIVE LOGITS
    Data
    0.39
     new
    0.36
    Factory
    0.36
     model
    0.34
    Form
    0.33
    class
    0.32
    Config
    0.32
    Client
    0.31
    Model
    0.31
    Manager
    0.31
    Activations Density 0.108%

    No Known Activations