© 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. 13120
    Prev
    Next
    INDEX
    Explanations

    results and outcomes

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

    adding results or numbers

    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
    하기도
    0.44
    這裡是
    0.42
     للح
    0.41
    ܨ
    0.38
     얘는
    0.38
    
    0.38
    外し
    0.38
    宥
    0.37
    रण
    0.37
    داخل
    0.37
    POSITIVE LOGITS
     resulting
    0.93
     newfound
    0.82
    resulting
    0.79
     aforementioned
    0.79
     resultant
    0.75
     findings
    0.73
     получен
    0.72
     newly
    0.71
     tersebut
    0.67
     resultante
    0.67
    Activations Density 0.170%

    No Known Activations