© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 46296
    Prev
    Next
    INDEX
    Explanations

    the your app or orders

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

    company names and technical products

    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
     caballos
    0.50
     الوطني
    0.42
    美人
    0.41
    َب
    0.41
    ्राष्ट
    0.41
    あるいは
    0.40
    発達
    0.40
    䖝
    0.40
     giorno
    0.40
     दुनियाभर
    0.40
    POSITIVE LOGITS
     Doh
    0.46
     Pank
    0.43
    st
    0.43
     utilising
    0.42
     effortlessly
    0.42
     Power
    0.42
    ın
    0.42
    의
    0.41
     Operation
    0.41
     Thunder
    0.40
    Activations Density 0.000%

    No Known Activations