© 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. 32685
    Prev
    Next
    INDEX
    Explanations

    SEARCHING FOR

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

    societies, author, technology, force, authority, friends

    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
     عندما
    0.52
    股东
    0.48
     దృష్టి
    0.46
     فأ
    0.44
     くれ
    0.44
     إليه
    0.44
    🔒
    0.43
     disple
    0.43
     निदेश
    0.43
     инвести
    0.42
    POSITIVE LOGITS
     backpacking
    0.49
    ;
    0.47
     surviving
    0.46
    trap
    0.46
    urow
    0.44
     available
    0.43
     termasuk
    0.43
    াসহ
    0.43
    <0x94>
    0.43
     disponibile
    0.42
    Activations Density 0.000%

    No Known Activations