© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 97385
    Prev
    Next
    INDEX
    Explanations

    campaigns, mission, wellness, video content

    np_acts-logits-general · gemini-2.5-flash-lite

    campaign idea generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    粖
    0.53
     औद्योगिक
    0.52
     पेट्रोलियम
    0.51
     churning
    0.50
    욧
    0.50
     industrialists
    0.48
     petroleum
    0.47
    出口
    0.46
    工業
    0.46
    畨
    0.45
    POSITIVE LOGITS
    achella
    0.50
     Snapchat
    0.50
    mersive
    0.48
     immersive
    0.47
     playfully
    0.47
    phone
    0.47
     influencers
    0.47
     astrophys
    0.46
     LGBTQ
    0.46
    icano
    0.46
    Activations Density 0.160%

    No Known Activations