© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69467
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     semp
    1.39
    тех
    1.38
    𝘇
    1.38
    adur
    1.38
     tweak
    1.33
     applicator
    1.32
     doughnut
    1.28
     celles
    1.26
     trainee
    1.26
    شش
    1.24
    POSITIVE LOGITS
     here
    1.33
    (
    1.27
    **
    1.24
    وت
    1.23
     Here
    1.21
    全文
    1.21
    Normally
    1.19
    原文
    1.18
    here
    1.18
    ores
    1.15
    Activations Density 0.000%

    No Known Activations