© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227859
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     hydrophobic
    0.45
     Committees
    0.45
     committees
    0.42
     subcommittee
    0.40
    子が
    0.40
    committees
    0.39
    侵
    0.39
    nem
    0.39
    िक
    0.38
    ों
    0.38
    POSITIVE LOGITS
     mutta
    0.43
    λλά
    0.42
    !';
    0.41
     แต่
    0.40
    extrait
    0.40
     ይ
    0.40
     භාවිත
    0.39
     crackers
    0.39
     सुनकर
    0.39
     ولكن
    0.38
    Activations Density 0.008%

    No Known Activations