© 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. 190397
    Prev
    Next
    INDEX
    Explanations

    latest innovative

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

    abstract concepts and intricate systems

    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
     favorably
    0.43
     Juga
    0.40
    modal
    0.40
    茼
    0.40
     કરવાની
    0.39
    身高
    0.39
    ûn
    0.39
    茆
    0.39
     همچنین
    0.39
    גם
    0.39
    POSITIVE LOGITS
     アル
    0.52
     empathy
    0.49
     pauses
    0.49
     compilers
    0.48
     sympathies
    0.47
     emulator
    0.47
     ซ
    0.47
     splashes
    0.47
     glitches
    0.46
    iobium
    0.46
    Activations Density 0.000%

    No Known Activations