© 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. 160295
    Prev
    Next
    INDEX
    Explanations

    words containing specific items

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

    military hierarchy or operation

    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
     kiedy
    0.50
    当我
    0.49
    笳
    0.49
    妘
    0.48
    চ্ছিলেন
    0.46
    醾
    0.46
     لما
    0.46
     keď
    0.46
     طريقة
    0.46
    ടെ
    0.45
    POSITIVE LOGITS
     authorizations
    0.51
     triples
    0.45
     blueprints
    0.45
     scrutin
    0.44
     crackdown
    0.44
     $(
    0.44
     feasibility
    0.43
     munitions
    0.43
     triple
    0.42
     वैधता
    0.42
    Activations Density 0.000%

    No Known Activations