© 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. 10101
    Prev
    Next
    INDEX
    Explanations

    additional

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

    additional / optional

    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
     ########.
    0.45
    単純
    0.44
     काय
    0.43
     אטאטורק
    0.43
     নৃশংস
    0.40
     เงี้ย
    0.40
    
    0.40
    }}}^{
    0.40
     baseY
    0.40
    jsonObject
    0.40
    POSITIVE LOGITS
     additional
    0.99
     dodat
    0.86
     zusätzlichen
    0.86
     zusätzliche
    0.85
     дополни
    0.83
     tambahan
    0.79
     thêm
    0.79
     Additional
    0.78
     дополнительных
    0.78
    additional
    0.77
    Activations Density 0.347%

    No Known Activations