© 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. 40-GEMMASCOPE-2-RES-262K
    7. 190957
    Prev
    Next
    INDEX
    Explanations

    specific types of text generation

    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
     charcoal
    0.38
    மம்
    0.38
     不同
    0.38
    /-
    0.37
    gua
    0.37
     மாசு
    0.37
    colas
    0.36
     shampoos
    0.36
     malonyl
    0.36
     teak
    0.35
    POSITIVE LOGITS
     Married
    0.40
     Show
    0.40
     Comput
    0.39
     bugs
    0.38
    结合
    0.38
    orne
    0.38
    炲
    0.38
     Explorer
    0.37
    ickey
    0.37
    珽
    0.37
    Activations Density 0.000%

    No Known Activations