© 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. 10-GEMMASCOPE-RES-131K
    7. 9216
    Prev
    Next
    INDEX
    Explanations

    right direction/position

    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
    </strong>
    -2.52
    “
    -2.34
     to
    -2.27
    {
    -2.09
     –
    -2.09
    ,
    -2.08
    ”
    -2.06
    …
    -2.03
    .
    -1.98
    (
    -1.94
    POSITIVE LOGITS
     secado
    2.45
     发型
    2.25
    阋
    2.17
     horloge
    2.16
     bricolaje
    2.16
     brille
    2.05
    felpa
    2.02
     gruppe
    2.02
     bús
    2.00
     calça
    1.99
    Activations Density 0.018%

    No Known Activations