© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2370
    Prev
    Next
    INDEX
    Explanations

    defining concepts or fields of study

    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
    dynamic
    0.38
     dynamic
    0.34
    spectral
    0.34
    properties
    0.33
     distinctions
    0.33
    transformed
    0.33
    static
    0.32
    }).
    0.32
     detailed
    0.32
    invariant
    0.32
    POSITIVE LOGITS
     Catholicism
    0.64
     politics
    0.61
     feminism
    0.61
     communism
    0.61
     capitalism
    0.58
     Christianity
    0.55
     fascism
    0.55
     socialism
    0.54
     academia
    0.53
     dentistry
    0.52
    Activations Density 0.032%

    No Known Activations