© 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. 10056
    Prev
    Next
    INDEX
    Explanations

    captions promoting home improvement services, specifically pressure washing.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    full

    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
    v
    0.80
    g
    0.78
    d
    0.71
    r
    0.64
    b
    0.62
    n
    0.60
    N
    0.59
    S
    0.59
    I
    0.58
    E
    0.58
    POSITIVE LOGITS
     full
    1.32
     FULL
    1.20
     Full
    1.16
     fully
    1.10
     volled
    1.08
     পূর্ণ
    1.02
     الكامل
    1.02
    Full
    1.01
    เต็ม
    1.01
    完整的
    0.99
    Activations Density 0.056%

    No Known Activations