© 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. 9573
    Prev
    Next
    INDEX
    Explanations

    prison and convict

    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
     Desktop
    0.42
     Fireworks
    0.42
     स्कूटर
    0.41
     localhost
    0.40
     ফাই
    0.40
     customer
    0.39
    emples
    0.39
    拈
    0.39
     müşter
    0.38
     Nest
    0.38
    POSITIVE LOGITS
     prison
    2.31
     inmates
    2.16
     inmate
    2.13
    Prison
    2.09
     Prison
    2.08
     prisoners
    2.06
     prisons
    2.03
    prison
    2.00
     prisoner
    2.00
    监狱
    1.86
    Activations Density 0.031%

    No Known Activations