© 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. 47346
    Prev
    Next
    INDEX
    Explanations

    negative numbers or comparisons

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

    language mix

    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
    ,
    0.59
     promulg
    0.55
     overwhelmingly
    0.47
     eing
    0.45
     INC
    0.44
    t
    0.44
     brows
    0.44
     appreciably
    0.44
     demands
    0.43
     lediglich
    0.43
    POSITIVE LOGITS
    ਸੀਂ
    0.53
    纽约
    0.50
    会話
    0.48
     न्यूयॉर्क
    0.48
     tahun
    0.45
    ൊപ്പം
    0.45
    いを
    0.44
    んな
    0.44
     લાગે
    0.44
    橢
    0.43
    Activations Density 0.000%

    No Known Activations