© 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. 202557
    Prev
    Next
    INDEX
    Explanations

    property, other, accept, shadows, meet, damaged, while

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

    processed, preceding, cities, expecting, developing

    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
    郧
    0.49
     pona
    0.49
    Ethyl
    0.48
    Acting
    0.48
     Phần
    0.45
    栈
    0.44
     Acting
    0.44
    Instant
    0.44
    的小
    0.43
    鲍
    0.43
    POSITIVE LOGITS
    heri
    0.62
     swelled
    0.55
     hyped
    0.55
     countrymen
    0.53
     geist
    0.51
    eken
    0.50
    eka
    0.49
    oran
    0.48
     nihil
    0.48
    še
    0.48
    Activations Density 0.000%

    No Known Activations