© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99969
    Prev
    Next
    INDEX
    Explanations

    ease, easily, effortlessly

    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
    -1.80
    踽
    -1.49
     then
    -1.41
     vogel
    -1.38
    ，”
    -1.34
     üz
    -1.30
     mostrarán
    -1.29
    袛
    -1.26
     nutri
    -1.24
    IGATION
    -1.24
    POSITIVE LOGITS
    If
    1.70
    There
    1.56
     якщо
    1.55
     It
    1.53
     немає
    1.43
    兩
    1.43
    🖇
    1.42
     If
    1.41
     walaupun
    1.41
    Using
    1.38
    Activations Density 0.023%

    No Known Activations