© 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. 83431
    Prev
    Next
    INDEX
    Explanations

    partnership and equality

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

    keywords followed by colon

    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
    ă
    0.58
    iliği
    0.53
    ৯০
    0.53
     de
    0.53
    irea
    0.50
    зия
    0.50
    یر
    0.49
    ীয়
    0.49
    疥
    0.48
    少的
    0.47
    POSITIVE LOGITS
    partner
    0.54
    partners
    0.50
     بنائے
    0.48
    mand
    0.47
    partnership
    0.46
     partners
    0.45
    musik
    0.45
     celebrations
    0.44
    pot
    0.44
    potent
    0.44
    Activations Density 0.000%

    No Known Activations