© 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. 203097
    Prev
    Next
    INDEX
    Explanations

    property, combined, secure, vintage

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

    accepting challenges or proposals

    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
    ایی
    0.42
     სპეცი
    0.42
     upstairs
    0.41
    十大
    0.41
     মুঠ
    0.41
     آموزش
    0.41
    クリル
    0.41
    《
    0.41
     yaşam
    0.41
     تقسيم
    0.40
    POSITIVE LOGITS
     consecut
    0.49
    Nums
    0.47
     checker
    0.46
     zero
    0.45
     stycz
    0.45
     workaround
    0.44
     consecutive
    0.44
     resul
    0.44
     една
    0.43
    ADT
    0.43
    Activations Density 0.005%

    No Known Activations