© 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. 40-GEMMASCOPE-2-RES-65K
    7. 52513
    Prev
    Next
    INDEX
    Explanations

    you embed

    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_40_width_65k_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
    琰
    0.43
    renewcommand
    0.39
     classifies
    0.38
     precludes
    0.38
     причем
    0.37
     deflected
    0.36
    GroupBy
    0.36
     作詞
    0.36
     chảy
    0.36
    ἓ
    0.35
    POSITIVE LOGITS
     сокра
    0.40
    annah
    0.39
     Organizational
    0.38
     soov
    0.38
    usermodel
    0.37
    unctional
    0.37
     Sociology
    0.37
     Sermon
    0.35
    uman
    0.34
     Funk
    0.34
    Activations Density 3.018%

    No Known Activations