© 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. 22-GEMMASCOPE-RES-131K
    7. 13221
    Prev
    Next
    INDEX
    Explanations

    Thursday, Turmeric, Q:

    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_22/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
    mappedBy
    -1.54
     egens
    -1.34
     perioden
    -1.30
     samti
    -1.27
     engelsk
    -1.21
     taal
    -1.18
     problemer
    -1.17
    ſſen
    -1.16
    räck
    -1.16
    moderne
    -1.14
    POSITIVE LOGITS
    :
    1.24
    。
    1.11
     and
    1.05
     thrombo
    1.02
    .
    1.00
     With
    0.99
     angefangen
    0.97
     zudem
    0.97
    ;
    0.97
     außerdem
    0.96
    Activations Density 0.006%

    No Known Activations