© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6489
    Prev
    Next
    INDEX
    Explanations

    Russian or Eastern European conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
    )}=
    0.39
     सज
    0.39
    )";
    0.38
     लि
    0.37
     έχ
    0.36
     seduce
    0.36
    )}_{\
    0.36
    UISelectors
    0.35
    डली
    0.35
     om
    0.35
    POSITIVE LOGITS
     Battles
    0.39
    anken
    0.37
     சுண்ணா
    0.36
     East
    0.36
     св
    0.36
    沫
    0.36
    imid
    0.35
     battles
    0.35
     Восто
    0.35
    Wald
    0.34
    Activations Density 0.029%

    No Known Activations