© 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. 31336
    Prev
    Next
    INDEX
    Explanations

    Mixtral

    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
    Gap
    0.43
     Gap
    0.41
    വ്
    0.40
    उ
    0.40
     competing
    0.39
    Uber
    0.38
    sl
    0.35
     Nim
    0.35
    テリア
    0.35
    ሶ
    0.35
    POSITIVE LOGITS
     mi
    0.49
     MI
    0.48
     Mi
    0.45
     millas
    0.43
     MIL
    0.42
    MIL
    0.41
     soldados
    0.40
     moléculas
    0.40
    ्रेंस
    0.39
    瓤
    0.39
    Activations Density 0.006%

    No Known Activations