© 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-65K
    7. 49442
    Prev
    Next
    INDEX
    Explanations

    ad extensions, students, conversational

    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_65k_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
     possiamo
    0.45
     BorderRadius
    0.44
    CodeDict
    0.44
    なんて
    0.44
    ό
    0.44
    几
    0.44
     รี
    0.44
    ᑦ
    0.44
    翮
    0.44
     നിർ
    0.44
    POSITIVE LOGITS
    amb
    0.40
    this
    0.39
    izes
    0.39
     conversational
    0.38
     ambigu
    0.38
     jedan
    0.37
    这个人
    0.37
     sigu
    0.37
    </sup>
    0.36
     kiln
    0.36
    Activations Density 0.010%

    No Known Activations