© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 17614
    Prev
    Next
    INDEX
    Explanations

    defined words

    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
    Island
    0.44
    Campbell
    0.39
    ARROW
    0.39
    island
    0.39
    島
    0.39
    ujan
    0.38
    Sound
    0.38
    iculis
    0.38
    William
    0.38
    British
    0.38
    POSITIVE LOGITS
     definido
    0.46
     Defined
    0.44
     definição
    0.44
    쌌
    0.43
     defined
    0.42
     reh
    0.42
     definition
    0.41
     usable
    0.41
     definiert
    0.40
     lower
    0.40
    Activations Density 0.002%

    No Known Activations