© 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-262K
    7. 27015
    Prev
    Next
    INDEX
    Explanations

    import models, induction programs

    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
     wanted
    0.43
    ᇁ
    0.42
     চায়
    0.40
    ほしい
    0.39
    欲しい
    0.38
     Winners
    0.38
     დარ
    0.38
    ႇ
    0.37
     fundraiser
    0.36
    輸入
    0.36
    POSITIVE LOGITS
     crying
    0.46
    migrations
    0.44
    cmd
    0.42
    wpi
    0.37
     você
    0.37
     famílias
    0.37
    nest
    0.36
     पीले
    0.36
    を用いる
    0.36
     الفصل
    0.36
    Activations Density 0.000%

    No Known Activations