© 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. 154712
    Prev
    Next
    INDEX
    Explanations

    list items or clauses

    np_acts-logits-general · gemini-2.5-flash-lite

    attached, step, eggs, role

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Gay
    0.52
     Gay
    0.52
    T
    0.51
     GY
    0.50
    τσ
    0.49
    Priority
    0.48
    Use
    0.48
    USE
    0.47
    S
    0.46
     Fris
    0.46
    POSITIVE LOGITS
     आध्यात्मिक
    0.52
     mesti
    0.52
     كتب
    0.50
     മറ്റൊരു
    0.49
     धार्मिक
    0.49
     bodhis
    0.48
     estructural
    0.47
     distinto
    0.47
     محسوس
    0.47
     عنه
    0.46
    Activations Density 0.001%

    No Known Activations