© 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. 184045
    Prev
    Next
    INDEX
    Explanations

    character Thanos, heavy formatting

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

    numbers and descriptions

    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
     nasa
    0.46
     isa
    0.46
    ⅓
    0.45
     дума
    0.44
     thermodynamics
    0.43
     formular
    0.43
     porque
    0.43
     neur
    0.42
    )
    0.42
    )]
    0.40
    POSITIVE LOGITS
    полни
    0.52
    TOTAL
    0.49
    Events
    0.47
     அனைத்து
    0.47
     总
    0.47
     ዓይነት
    0.47
    ఫో
    0.45
    舟
    0.44
    ບໍລິ
    0.44
     ebenso
    0.44
    Activations Density 0.000%

    No Known Activations