© 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. 105458
    Prev
    Next
    INDEX
    Explanations

    names of entities or places

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

    building a list

    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
    用意
    0.43
    疝
    0.43
    assian
    0.43
    基金产品
    0.42
    hdf
    0.42
     alanine
    0.42
    样本
    0.42
     alphanumeric
    0.41
    বাহিনীর
    0.41
    adf
    0.41
    POSITIVE LOGITS
     لذلك
    0.49
    豊富
    0.48
    鱉
    0.46
     भरपूर
    0.46
    Connecticut
    0.46
     পরিবর্তন
    0.45
     Einige
    0.44
    যদিও
    0.43
    carte
    0.42
     abound
    0.42
    Activations Density 0.000%

    No Known Activations