© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152552
    Prev
    Next
    INDEX
    Explanations

    Russia Ukraine conflict aid

    np_acts-logits-general · gemini-2.5-flash-lite

    Russia invade Ukraine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     septic
    0.45
     २०२
    0.41
     supabase
    0.41
     freuen
    0.40
     relat
    0.40
    🤎
    0.40
     kesan
    0.39
     unspoken
    0.39
    🥲
    0.39
     masking
    0.38
    POSITIVE LOGITS
     തുടങ്ങി
    0.44
    Bone
    0.43
     पाण
    0.41
    🎿
    0.41
    姿勢
    0.40
    Lengths
    0.40
    蟒
    0.40
    🍪
    0.39
    陘
    0.39
    Lite
    0.38
    Activations Density 0.001%

    No Known Activations