© 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. 212528
    Prev
    Next
    INDEX
    Explanations

    Crypto transactions and related concepts

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

    dog meat consumption

    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
    ิน
    0.48
    ру
    0.47
     and
    0.47
    ە
    0.46
    ח
    0.45
    ի
    0.45
    ко
    0.45
     vis
    0.44
    0.43
    ש
    0.43
    POSITIVE LOGITS
    বাক
    0.51
     التجارية
    0.48
    拶
    0.47
    াধীন
    0.45
     विभक्ति
    0.45
    စိတ်အပိုင်း
    0.44
     कुटुंबा
    0.44
     práctico
    0.43
     ။
    0.43
    劷
    0.43
    Activations Density 0.001%

    No Known Activations