© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13501
    Prev
    Next
    INDEX
    Explanations

    companion or close associate

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

    companion develops

    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
    聚焦
    0.55
    ܸ
    0.48
    एँ
    0.48
    ೮
    0.46
     затем
    0.46
     बीएस
    0.46
    resultados
    0.46
     अस्पतालों
    0.46
    আমরা
    0.46
    œ
    0.46
    POSITIVE LOGITS
     companion
    0.77
     companions
    0.69
     companionship
    0.66
     Companion
    0.65
    companion
    0.65
     aide
    0.64
     aides
    0.64
     entourage
    0.64
     compagn
    0.64
    助手
    0.63
    Activations Density 0.072%

    No Known Activations