© 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. 79250
    Prev
    Next
    INDEX
    Explanations

    except along, plus sign, varied preliminary, Certified Pre

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

    punctuation and challenge

    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
    as
    0.41
     homogenous
    0.39
    Eh
    0.39
     இதுபோன்ற
    0.39
    Ħ
    0.39
     monoc
    0.39
     multiplicative
    0.38
     نباش
    0.38
    ܥ
    0.37
     Paese
    0.37
    POSITIVE LOGITS
     των
    0.53
    จากการ
    0.47
     божо
    0.45
     вскоре
    0.45
     зачем
    0.43
     четы
    0.43
    лия
    0.43
     από
    0.42
     दलों
    0.42
    쥔
    0.42
    Activations Density 0.001%

    No Known Activations