© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27726
    Prev
    Next
    INDEX
    Explanations

    breakdown of

    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
     Wikipédia
    0.49
    ?!?!
    0.46
    ™,
    0.45
    📋
    0.45
    <b>
    0.43
    !),
    0.43
    ToPointer
    0.42
    !”,
    0.42
     GUID
    0.41
     Essentials
    0.41
    POSITIVE LOGITS
     ,
    0.55
     :"
    0.52
    ੲ
    0.50
     .(
    0.48
     পুর্ব
    0.48
     expt
    0.46
     peuvent
    0.45
     लिये
    0.45
     వు
    0.45
    ocole
    0.44
    Activations Density 0.161%

    No Known Activations