© 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. 7570
    Prev
    Next
    INDEX
    Explanations

    named entities, specifically organizations and companies.

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

    contrast and addition

    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
    ㅎ
    0.29
    oarece
    0.27
     saling
    0.26
    व्
    0.26
    િ
    0.25
     senjata
    0.25
    𝟘
    0.25
    ู้
    0.24
     pues
    0.24
     mâles
    0.24
    POSITIVE LOGITS
    ก็
    0.35
     dennoch
    0.34
     may
    0.33
    也可以
    0.33
    这不是
    0.31
     cannot
    0.31
     also
    0.31
    은
    0.30
    并不是
    0.30
    也
    0.29
    Activations Density 0.063%

    No Known Activations