© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7061
    Prev
    Next
    INDEX
    Explanations

    "is no" or "is a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vrier
    -1.26
     cualquier
    -1.20
     tamaño
    -1.19
     любой
    -1.14
     qualsiasi
    -1.09
    ขอบคุณ
    -1.09
     qualquer
    -1.07
    ﾚ
    -1.06
    ₒ
    -1.05
    慄
    -1.03
    POSITIVE LOGITS
     no
    2.05
     certain
    1.75
     need
    1.66
     some
    1.58
     hardly
    1.52
     also
    1.45
     a
    1.41
     plenty
    1.38
     few
    1.31
     two
    1.24
    Activations Density 0.067%

    No Known Activations