© 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. 173356
    Prev
    Next
    INDEX
    Explanations

    ratio of

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

    economic concepts, collapsing possibilities

    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
    ğı
    0.46
     아트
    0.45
     рук
    0.44
    <>();
    0.44
     innovate
    0.44
     प्रोट
    0.43
    PLAT
    0.42
    <>());
    0.42
    getStringExtra
    0.41
     univerz
    0.41
    POSITIVE LOGITS
    Khi
    0.47
    த்தகைய
    0.46
     باوجود
    0.43
    膻
    0.43
    ernacle
    0.43
     होला
    0.43
    ठबंधन
    0.43
    ানু
    0.42
    IZATION
    0.41
    -\
    0.41
    Activations Density 0.001%

    No Known Activations