© 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. 172384
    Prev
    Next
    INDEX
    Explanations

    news and narratives

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

    predictable movements and advancement

    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
    utuskan
    0.54
     stomachs
    0.50
     puedan
    0.49
    estomac
    0.48
     कल
    0.47
    ่
    0.47
     умень
    0.47
     または
    0.45
    ğ
    0.45
     ወይም
    0.44
    POSITIVE LOGITS
     standoff
    0.50
     consistently
    0.45
     disbelief
    0.44
     reliably
    0.43
     memoir
    0.43
     subpoena
    0.43
     lash
    0.42
     bestseller
    0.41
    מר
    0.41
    ਆ
    0.41
    Activations Density 0.000%

    No Known Activations