© 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. 113429
    Prev
    Next
    INDEX
    Explanations

    collaboration and partnership

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

    partners and collaborations

    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
     BlueprintName
    0.49
     groupBox
    0.46
     সংসার
    0.46
     isomorphisms
    0.45
     Anschluss
    0.45
    甚至
    0.44
    Acetoxy
    0.44
    狎
    0.44
    ピソード
    0.44
    😒
    0.44
    POSITIVE LOGITS
     partners
    0.98
    partners
    0.96
     partnered
    0.93
     partnering
    0.93
     partenaires
    0.87
    partner
    0.86
     partner
    0.84
     colaboración
    0.82
     collaborating
    0.82
     совместно
    0.82
    Activations Density 0.123%

    No Known Activations