© 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. 252834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    slave
    0.45
    basin
    0.44
    wen
    0.43
    <0x0D>
    0.42
    mi
    0.42
    </b>
    0.41
    ni
    0.41
    dao
    0.41
     şeyi
    0.41
    than
    0.40
    POSITIVE LOGITS
    ⚊
    0.51
    𒂵
    0.49
    殚
    0.49
     oftentimes
    0.49
    मताओं
    0.48
    दरअसल
    0.48
     resorting
    0.48
     adverts
    0.47
     Рі
    0.47
    ಂಟ
    0.47
    Activations Density 0.000%

    No Known Activations