© 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. 31-GEMMASCOPE-2-RES-262K
    7. 112207
    Prev
    Next
    INDEX
    Explanations

    general internet trends

    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_31_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
    anlı
    0.52
    automated
    0.47
    죄
    0.45
    ває
    0.44
    ào
    0.43
    ம்
    0.42
    τά
    0.42
     přij
    0.42
    produce
    0.42
    𝒶
    0.41
    POSITIVE LOGITS
    skar
    0.47
    tu
    0.46
    sorption
    0.46
     металли
    0.46
    t
    0.45
     пропа
    0.45
    د
    0.45
     সম
    0.44
     બધા
    0.44
    s
    0.44
    Activations Density 0.006%

    No Known Activations