© 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. 30477
    Prev
    Next
    INDEX
    Explanations

    anarchist, capitalist, destruction, topics

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

    political isms

    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
    жала
    0.49
    梦
    0.46
    Coral
    0.45
    мон
    0.44
    Another
    0.44
    Accordion
    0.44
    趸
    0.43
    奂
    0.43
    Brewer
    0.43
    Surely
    0.43
    POSITIVE LOGITS
     anarch
    0.50
     destruction
    0.48
     capitalists
    0.43
     நா
    0.42
     destroyer
    0.42
     denounced
    0.42
     capitalist
    0.41
     වීම
    0.40
     destru
    0.40
     prolet
    0.39
    Activations Density 0.011%

    No Known Activations