© 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. 128652
    Prev
    Next
    INDEX
    Explanations

    Trump said

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

    for purpose. property/time. attractive qualities. relationships. advice. things

    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
     جمعیت
    0.48
    氹
    0.47
    📏
    0.46
     conjuntos
    0.45
     کش
    0.44
    ঁয়
    0.44
    歐洲
    0.43
    îte
    0.42
     Quadrat
    0.41
    Ê
    0.41
    POSITIVE LOGITS
    izawa
    0.45
     phag
    0.43
     Зараз
    0.43
    사
    0.42
    acakt
    0.42
    дика
    0.41
    irar
    0.41
    iculos
    0.41
     electrolyte
    0.41
     electrolytes
    0.41
    Activations Density 0.000%

    No Known Activations