© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60443
    Prev
    Next
    INDEX
    Explanations

    question asking what

    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
     such
    -1.48
     bastion
    -1.40
    pirable
    -1.30
     seem
    -1.27
    arashtra
    -1.26
    such
    -1.25
    acité
    -1.20
    耵
    -1.20
     visión
    -1.20
     and
    -1.19
    POSITIVE LOGITS
    )
    1.88
     other
    1.63
    n
    1.52
     decreasing
    1.51
     what
    1.49
    時間を
    1.47
    ományos
    1.40
    家を
    1.38
     japones
    1.38
    各种
    1.37
    Activations Density 0.063%

    No Known Activations