© 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. 241377
    Prev
    Next
    INDEX
    Explanations

    solution torefer toseparate suites

    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
     लक्ष्य
    0.51
    工资
    0.50
     θεω
    0.50
     цель
    0.49
    镤
    0.48
    larını
    0.48
     IUnary
    0.47
    㿝
    0.47
     симпто
    0.47
     উদ্দেশ্য
    0.47
    POSITIVE LOGITS
     cacao
    0.51
    (
    0.46
     fabrics
    0.45
     goods
    0.45
     pirate
    0.45
     geographies
    0.44
     chocolate
    0.44
     heightened
    0.44
     editable
    0.44
     women
    0.43
    Activations Density 0.001%

    No Known Activations