© 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. 222444
    Prev
    Next
    INDEX
    Explanations

    FORM MAKE

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

    technical terms and processes

    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
     patriotic
    0.54
     underlying
    0.49
     deve
    0.48
     obej
    0.47
    er
    0.46
     dictators
    0.46
    ");*/
    0.46
     retali
    0.46
     variant
    0.45
     patriotism
    0.45
    POSITIVE LOGITS
     राजमार्ग
    0.48
    翮
    0.46
    濑
    0.45
     técnica
    0.45
    Departamento
    0.45
     técnicas
    0.44
    Pré
    0.44
    器的
    0.43
     निलंबित
    0.43
    Preface
    0.43
    Activations Density 0.000%

    No Known Activations