© 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. 31-GEMMASCOPE-2-RES-65K
    7. 16497
    Prev
    Next
    INDEX
    Explanations

    "sh" followed by specific words

    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_31_width_65k_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
    us
    0.75
    is
    0.71
    so
    0.70
    ssa
    0.67
    t
    0.66
    has
    0.66
    𝐬
    0.63
    的功能
    0.62
    ress
    0.62
    son
    0.62
    POSITIVE LOGITS
     fluv
    0.71
     сообщили
    0.71
    o
    0.68
     ſh
    0.67
     sh
    0.66
     relatório
    0.66
    Britain
    0.66
     forcefully
    0.65
    ב
    0.65
    вини
    0.64
    Activations Density 0.374%

    No Known Activations