© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8256
    Prev
    Next
    INDEX
    Explanations

    Bring on / Ask me / Relax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    0.36
            
    0.32
                    
    0.32
     +
    0.32
    ר
    0.31
     à
    0.30
     để
    0.30
     in
    0.30
     both
    0.30
     various
    0.30
    POSITIVE LOGITS
     pierwszy
    0.36
    どんどん
    0.34
     लिखिए
    0.34
    leyin
    0.33
    狠狠
    0.33
    쫌
    0.33
     pierwsze
    0.32
     jezik
    0.31
    とにかく
    0.31
    걍
    0.31
    Activations Density 0.158%

    No Known Activations