© 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. 55966
    Prev
    Next
    INDEX
    Explanations

    march, family, friendships, foreign concepts

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

    abstract qualities and relationships

    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
     ilgili
    0.45
    陂
    0.44
    应该是
    0.43
    썸
    0.43
     cycled
    0.43
    哧
    0.42
    ாத
    0.40
     описа
    0.40
    轱
    0.39
     పొ
    0.39
    POSITIVE LOGITS
     negotiations
    0.52
     friendships
    0.46
     বিলা
    0.44
     透明
    0.44
    独自の
    0.44
     intelekt
    0.44
     Beziehungen
    0.44
     他们
    0.43
     délé
    0.43
     dirigeants
    0.42
    Activations Density 0.000%

    No Known Activations