© 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. 40-GEMMASCOPE-2-RES-65K
    7. 51349
    Prev
    Next
    INDEX
    Explanations

    Greg Brown, Rutkowski, Alan Isakov

    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_40_width_65k_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
    ជាក់
    0.40
    imester
    0.39
    vap
    0.39
     الحق
    0.38
    ষ্
    0.38
    ետ
    0.38
    車站
    0.37
    }});
    0.37
    </i>
    0.37
     $
    0.37
    POSITIVE LOGITS
     indire
    0.69
     indirectly
    0.68
     indirect
    0.66
     Indirect
    0.64
    Indirect
    0.64
    indirect
    0.64
    ORY
    0.56
     INDIRECT
    0.55
    ório
    0.47
    orio
    0.46
    Activations Density 0.006%

    No Known Activations