© 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. 162810
    Prev
    Next
    INDEX
    Explanations

    estimated deaths

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

    terms, questions, or items

    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
    rę
    0.51
    Chats
    0.51
    му
    0.46
    ောင်း
    0.45
    ルー
    0.45
    මණ
    0.45
    ප
    0.44
    Cube
    0.44
    
    0.43
    са
    0.43
    POSITIVE LOGITS
     auquel
    0.48
     причем
    0.48
     anden
    0.47
     empr
    0.47
     auxquels
    0.47
     attest
    0.46
     laquelle
    0.46
     utiles
    0.46
     fortiter
    0.46
     MDET
    0.46
    Activations Density 0.001%

    No Known Activations