© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5213
    Prev
    Next
    INDEX
    Explanations

    European places and maps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ].
    1.24
    ↵↵
    1.15
    ine
    1.11
    sth
    1.03
    }.
    1.02
    .
    1.02
    ]
    1.01
    .]
    1.00
    isim
    0.97
    staticmethod
    0.96
    POSITIVE LOGITS
    かつ
    1.35
    uitary
    1.29
     Koss
    1.23
    ствовал
    1.22
    ريض
    1.20
    schemaLocation
    1.19
    Ey
    1.17
     orthodontic
    1.16
     aad
    1.16
     dentists
    1.14
    Activations Density 0.084%

    No Known Activations