© 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. 252737
    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
    ת
    0.54
     चंद
    0.53
     ($_
    0.51
     čast
    0.50
    丈
    0.50
     삽니다
    0.48
    ר
    0.48
    ؟!
    0.47
     sprechen
    0.47
     формирования
    0.47
    POSITIVE LOGITS
     failure
    0.49
     sea
    0.48
     phosphate
    0.48
    sea
    0.47
     touching
    0.47
     battery
    0.47
     knowledge
    0.46
    ರಿ
    0.46
     confidence
    0.45
     mountainous
    0.45
    Activations Density 0.001%

    No Known Activations