© 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. 28198
    Prev
    Next
    INDEX
    Explanations

    specific entities followed by context

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

    dangerous situations and decisions

    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
     estis
    0.46
    ranged
    0.46
    நான்
    0.44
     높은
    0.43
    people
    0.43
     edged
    0.41
     buvo
    0.40
    많
    0.40
    employees
    0.40
    хоро
    0.40
    POSITIVE LOGITS
     fantasy
    0.48
     system
    0.47
     schema
    0.47
    ！！！
    0.47
     syst
    0.44
     processus
    0.44
    ！！！！
    0.43
    妄
    0.43
     আবিষ্কার
    0.43
    方案
    0.43
    Activations Density 0.000%

    No Known Activations