© 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. 190809
    Prev
    Next
    INDEX
    Explanations

    English to English

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

    simpler, basic, or current state

    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
     insuficiente
    0.51
    ϒ
    0.51
    涷
    0.50
    engah
    0.50
    ㄑ
    0.49
    琹
    0.49
     fehlen
    0.48
    Insufficient
    0.47
    鉻
    0.47
    τητας
    0.46
    POSITIVE LOGITS
     Honda
    0.46
     EVERY
    0.46
     Everywhere
    0.44
     Baby
    0.44
     blossoms
    0.44
     Trojan
    0.44
     Sonora
    0.43
     Maui
    0.43
     Bal
    0.43
     cosmetic
    0.43
    Activations Density 0.000%

    No Known Activations