© 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. 246410
    Prev
    Next
    INDEX
    Explanations

    saving and processing

    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
     কিংবা
    0.57
    藓
    0.54
    あるいは
    0.53
     یا
    0.51
     pien
    0.50
     SupCt
    0.48
     hendak
    0.48
     αί
    0.47
     homotopy
    0.47
     সম্মুখে
    0.46
    POSITIVE LOGITS
    3
    0.57
    az
    0.56
    ob
    0.55
    1
    0.55
    R
    0.55
    mar
    0.54
    OT
    0.53
    par
    0.52
    Y
    0.52
    CH
    0.52
    Activations Density 0.001%

    No Known Activations