© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226496
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    0.42
    োয়
    0.41
    onda
    0.41
    elem
    0.40
    ovin
    0.39
    adid
    0.39
    clud
    0.38
    addTo
    0.38
    indahkan
    0.38
    drift
    0.38
    POSITIVE LOGITS
    ΙΑ
    0.46
     médias
    0.45
    भ
    0.45
    ികളും
    0.43
    न्ध
    0.43
    ികൾ
    0.42
    ته
    0.42
     श्रीवास्तव
    0.42
    ວ
    0.42
    OTH
    0.42
    Activations Density 0.002%

    No Known Activations