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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 9850
    Prev
    Next
    INDEX
    Explanations

    entity association

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ંત્ર
    0.42
     improvised
    0.41
     insidious
    0.41
     oblivion
    0.41
    emphasis
    0.40
     ozbil
    0.40
    ੫
    0.40
    تل
    0.39
    idega
    0.39
     scarcely
    0.38
    POSITIVE LOGITS
    关联
    1.14
     associated
    1.01
     assoc
    0.96
     assigned
    0.93
     association
    0.91
     affiliations
    0.91
     asociada
    0.91
     associating
    0.90
    所属
    0.90
     associé
    0.89
    Activations Density 0.060%

    No Known Activations