© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 214055
    Prev
    Next
    INDEX
    Explanations

    hundreds and thousands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     :
    0.38
     ,
    0.37
     ข
    0.35
    Cet
    0.35
    С
    0.35
    痺
    0.35
     সন্দেহ
    0.34
    /,
    0.34
     це
    0.34
    จะได้
    0.34
    POSITIVE LOGITS
    三百
    0.57
     cientos
    0.53
     hundreds
    0.51
     Hundreds
    0.49
     ஆயிரம்
    0.45
     ratus
    0.45
     centena
    0.44
    Hundreds
    0.43
    hundred
    0.42
    数百
    0.42
    Activations Density 0.008%

    No Known Activations