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

    Neuronpedia

    Jacobian LensNEW
    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. 1366
    Prev
    Next
    INDEX
    Explanations

    explore

    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
         
    0.49
     often
    0.48
     সাধারণত
    0.47
     generally
    0.46
    <unused2172>
    0.46
     usually
    0.45
     ,
    0.43
    <unused2121>
    0.43
     généralement
    0.43
     altid
    0.43
    POSITIVE LOGITS
     absurdity
    0.58
     ludicrous
    0.57
     ridiculous
    0.57
     badass
    0.54
     glorious
    0.54
     reimag
    0.53
     absurd
    0.52
     delicioso
    0.50
     chimeric
    0.50
    这将
    0.49
    Activations Density 0.903%

    No Known Activations