© 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. 31-GEMMASCOPE-2-RES-16K
    7. 894
    Prev
    Next
    INDEX
    Explanations

    Key improvements and tension

    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_31_width_16k_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
    ędzie
    0.39
    ziu
    0.36
    ify
    0.35
    ēt
    0.35
    既
    0.35
     być
    0.35
    ті
    0.35
    U
    0.35
    वर
    0.34
    сию
    0.34
    POSITIVE LOGITS
    OLYBDENUM
    0.44
     incl
    0.41
     （
    0.38
     tijekom
    0.38
    gmzy
    0.38
    （
    0.38
    }>
    0.37
    including
    0.37
     следующие
    0.37
    INCLUDING
    0.37
    Activations Density 0.511%

    No Known Activations