© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47974
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun

    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_10/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
     teşekkür
    -1.56
    genicity
    -1.51
     британ
    -1.39
     basit
    -1.34
     solamente
    -1.33
     admiten
    -1.32
    が多い
    -1.31
    durante
    -1.30
     unbelievably
    -1.30
    ांकि
    -1.30
    POSITIVE LOGITS
     with
    1.66
     their
    1.62
     можли
    1.41
     завжди
    1.39
    their
    1.38
    他の
    1.37
    $}
    1.34
     sorella
    1.33
    باره
    1.33
     Before
    1.31
    Activations Density 0.203%

    No Known Activations