© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135335
    Prev
    Next
    INDEX
    Explanations

    due to, girl, pride, experience

    np_acts-logits-general · gemini-2.5-flash-lite

    cuts, means, or properties of a design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    0.56
     環
    0.48
    you
    0.48
     তুমি
    0.46
    біт
    0.46
    ず
    0.46
    環
    0.46
    remain
    0.45
    νό
    0.44
    請
    0.44
    POSITIVE LOGITS
     kræ
    0.46
     membutuhkan
    0.43
     Fortsch
    0.43
     kontroll
    0.42
     الماض
    0.42
     konst
    0.41
     त्याने
    0.41
     મંદિર
    0.40
     risky
    0.40
    ột
    0.39
    Activations Density 0.001%

    No Known Activations