© 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. 10807
    Prev
    Next
    INDEX
    Explanations

    descriptions of technology companies and their innovations.

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

    demonstrating interest or qualities

    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
    z
    0.68
     TO
    0.57
    zf
    0.54
    to
    0.54
     storyteller
    0.54
    zov
    0.53
    ：
    0.53
    us
    0.53
     story
    0.50
     TE
    0.49
    POSITIVE LOGITS
     zeigen
    0.80
     signes
    0.73
     signs
    0.70
     демонстри
    0.70
     eagerness
    0.67
    Signs
    0.66
     signos
    0.65
     Showing
    0.62
     demonstrating
    0.62
     prowess
    0.62
    Activations Density 0.104%

    No Known Activations