© 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. 21189
    Prev
    Next
    INDEX
    Explanations

    alternate political futures

    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
    仕組み
    0.48
    시스템
    0.47
    㖪
    0.43
    chyné
    0.41
    ळे
    0.41
    घा
    0.41
    رآ
    0.41
    //$
    0.40
     recipiente
    0.40
    듦
    0.40
    POSITIVE LOGITS
     cyberpunk
    0.66
     cyborg
    0.57
     reformed
    0.55
     steampunk
    0.52
     bolstered
    0.51
     militias
    0.51
     ██
    0.51
     diverges
    0.50
     oligarch
    0.50
     cyber
    0.49
    Activations Density 0.015%

    No Known Activations