© 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. 12114
    Prev
    Next
    INDEX
    Explanations

    software development kits

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

    SDKs and APIs for developers

    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
     शास्त्र
    0.57
     fdPar
    0.57
    鮋
    0.55
    OGRAPH
    0.55
    頚
    0.55
    fdPar
    0.54
    bathy
    0.53
    symplectic
    0.53
    疖
    0.53
    骯
    0.52
    POSITIVE LOGITS
     SDK
    0.98
    SDK
    0.93
    sdk
    0.86
     Android
    0.82
     sdk
    0.79
    Android
    0.76
    Sdk
    0.75
     android
    0.69
     monetization
    0.68
     iOS
    0.68
    Activations Density 0.034%

    No Known Activations