© 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. 16803
    Prev
    Next
    INDEX
    Explanations

    accusing and naming/shaming groups

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

    claims about ideologies

    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
     Suite
    0.48
     Besançon
    0.47
     FHD
    0.45
     Obsidian
    0.45
    _
    0.45
     optimised
    0.44
     सर्वोत्तम
    0.43
     Robotic
    0.43
     Shaw
    0.43
     Optimized
    0.43
    POSITIVE LOGITS
     ktorí
    0.57
    譴
    0.57
    regarding
    0.55
     resentment
    0.55
    罵
    0.55
     щодо
    0.50
     bureaucrats
    0.50
     populist
    0.50
    詆
    0.50
     quienes
    0.49
    Activations Density 0.002%

    No Known Activations