© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133358
    Prev
    Next
    INDEX
    Explanations

    sequence processing

    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_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
     пад
    0.44
     eux
    0.43
    Acknowledg
    0.39
     ờ
    0.38
    ствуют
    0.38
     ihnen
    0.37
     vzh
    0.37
    Acknowled
    0.37
    ляє
    0.37
    蓋
    0.37
    POSITIVE LOGITS
     Web
    0.44
    Web
    0.44
     preceded
    0.44
    wheel
    0.42
     Worldwide
    0.41
     laboratory
    0.40
     Earlier
    0.40
     earlier
    0.40
     Corpus
    0.40
     locates
    0.39
    Activations Density 0.000%

    No Known Activations