© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    months in dates

    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
    ╒
    -1.17
    лимпий
    -1.11
    Samstag
    -1.11
     dió
    -1.09
    Ferien
    -1.09
     editText
    -1.06
     randonnée
    -1.05
     testen
    -1.05
    ogast
    -1.05
    ánt
    -1.04
    POSITIVE LOGITS
     to
    1.14
     death
    1.08
    cubo
    1.02
     her
    1.00
     Послед
    0.99
     his
    0.96
     and
    0.95
    ,
    0.94
     persönliche
    0.93
    yil
    0.91
    Activations Density 0.061%

    No Known Activations