© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35242
    Prev
    Next
    INDEX
    Explanations

    '; statements and declarations

    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
    İN
    -1.03
    バム
    -0.98
     skeletons
    -0.96
    時間も
    -0.93
    ケティング
    -0.93
    してる
    -0.93
    楢
    -0.93
    then
    -0.92
    啰
    -0.92
    桝
    -0.90
    POSITIVE LOGITS
     sterke
    1.13
     ensimmä
    1.07
     ersten
    1.06
    ujuk
    1.04
     traditionnelle
    1.04
     consideran
    1.03
    Спољашње
    1.00
     hermosas
    1.00
     setelah
    0.99
     other
    0.99
    Activations Density 0.026%

    No Known Activations