© 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. 8302
    Prev
    Next
    INDEX
    Explanations

    to

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     парамет
    0.19
     щоб
    0.19
    })]
    0.18
    转换
    0.18
    }))
    0.18
     activeButton
    0.18
     клю
    0.18
     anzeigen
    0.17
     gespe
    0.17
     sogenannte
    0.17
    POSITIVE LOGITS
    ppled
    0.27
     a
    0.26
    ppling
    0.24
    ge
    0.24
     the
    0.24
    기
    0.23
    지
    0.23
     have
    0.22
    ס
    0.22
    pple
    0.22
    Activations Density 0.526%

    No Known Activations