© 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. 133188
    Prev
    Next
    INDEX
    Explanations

    investigation and dissent

    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
     гидро
    0.45
     карту
    0.45
    문
    0.44
     rosso
    0.43
    othy
    0.43
    Firing
    0.43
    紅
    0.42
     Пред
    0.41
     Ку
    0.40
     фор
    0.40
    POSITIVE LOGITS
     investigation
    0.40
     investigative
    0.40
     hiked
    0.39
     Investigative
    0.39
    Airbnb
    0.38
    ingredient
    0.38
     '@/
    0.38
     investigations
    0.38
     Investig
    0.37
     jailed
    0.37
    Activations Density 0.004%

    No Known Activations