© 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. 132306
    Prev
    Next
    INDEX
    Explanations

    American cooks, women, gals, collaboration, physical modification

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

    synonym or descriptive phrase

    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
    )',
    0.47
    didn
    0.47
    रहे
    0.46
    ्यारह
    0.45
    bollah
    0.44
    described
    0.44
    ()=>{
    0.44
    rdquo
    0.43
     व्यवसाय
    0.43
     नव्ह
    0.43
    POSITIVE LOGITS
     modificación
    0.52
    _
    0.51
    ການ
    0.47
     اضاف
    0.46
     fisica
    0.46
     lắng
    0.45
     thêm
    0.45
    对象的
    0.44
    互相
    0.44
     modifica
    0.43
    Activations Density 0.001%

    No Known Activations