© 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. 253131
    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
     풀
    0.54
    ದಲ್ಲಿ
    0.48
    尴
    0.48
    ständen
    0.47
    轸
    0.47
    شو
    0.46
    忘了
    0.46
    NonUser
    0.46
    Consent
    0.45
     Validación
    0.45
    POSITIVE LOGITS
    t
    0.58
    1
    0.53
     t
    0.51
     u
    0.49
     regio
    0.48
     patriotism
    0.47
     relativity
    0.47
     lineWidth
    0.46
    2
    0.46
     n
    0.46
    Activations Density 0.000%

    No Known Activations