© 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. 21287
    Prev
    Next
    INDEX
    Explanations

    Rodgers, coolant, rocker

    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
    𝄆
    -2.88
     {
    -2.41
     остальные
    -2.36
    鍆
    -2.28
    e
    -2.28
    孓
    -2.25
    eyes
    -2.23
    鐒
    -2.16
    ⢌
    -2.11
    .
    -2.09
    POSITIVE LOGITS
     erzählen
    3.56
    \
    3.02
     This
    2.59
    The
    2.58
    珦
    2.55
    这种
    2.53
    世界
    2.47
     tweaked
    2.45
     THE
    2.39
    状況
    2.39
    Activations Density 0.003%

    No Known Activations