© 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. 258475
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    óm
    0.49
    };
    0.49
    ili
    0.47
    isn
    0.46
    ];
    0.45
    chn
    0.45
    executionContext
    0.45
    绢
    0.45
    manifest
    0.44
    帮忙
    0.44
    POSITIVE LOGITS
     liquidation
    0.56
     detour
    0.55
     avenue
    0.54
     annuities
    0.54
     sedan
    0.53
     medley
    0.52
     Category
    0.52
     cartel
    0.52
     fraternal
    0.52
     donor
    0.51
    Activations Density 0.000%

    No Known Activations