© 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. 88793
    Prev
    Next
    INDEX
    Explanations

    why do

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

    common phrases and structures

    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
    ays
    0.50
     সম্ভাব্য
    0.47
    ine
    0.47
    atic
    0.44
    ård
    0.43
    boi
    0.43
     emery
    0.43
     正
    0.43
     hæ
    0.43
    élène
    0.43
    POSITIVE LOGITS
    ພວກເຮົາ
    0.46
     simplemente
    0.46
    講解
    0.45
     primavera
    0.43
    ர்களில்
    0.43
     sadr
    0.43
     springboard
    0.43
    集群
    0.42
    स्तरीय
    0.42
     semplicemente
    0.41
    Activations Density 0.000%

    No Known Activations