© 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. 152669
    Prev
    Next
    INDEX
    Explanations

    word pairs or collocations

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

    specific scenarios or conditions

    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
     automática
    0.47
    нос
    0.46
    吕
    0.46
    畴
    0.46
    だな
    0.45
     concentrated
    0.45
    鄰
    0.44
    短期
    0.44
    呂
    0.44
    ்
    0.44
    POSITIVE LOGITS
     Behav
    0.52
     Tan
    0.52
     Empres
    0.48
     Support
    0.47
     Effect
    0.46
     Throughout
    0.46
     TAN
    0.45
     Interference
    0.45
    achts
    0.45
     Incidence
    0.45
    Activations Density 0.001%

    No Known Activations