© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2636
    Prev
    Next
    INDEX
    Explanations

    spending time or points

    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_16_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
    اب
    1.39
    was
    1.37
    b
    1.23
    ays
    1.19
    is
    1.18
    وس
    1.14
    a
    1.12
    up
    1.11
    set
    1.09
    ло
    1.09
    POSITIVE LOGITS
     invertir
    1.18
     dinast
    1.17
     bombard
    1.16
     manufactures
    1.11
     forze
    1.10
    ,
    1.09
    ཎ
    1.09
     divulg
    1.09
    ⦖
    1.09
     incend
    1.08
    Activations Density 0.201%

    No Known Activations