© 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. 22-GEMMASCOPE-RES-131K
    7. 64921
    Prev
    Next
    INDEX
    Explanations

    text alignment

    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
     to
    -2.00
    などを
    -1.21
     during
    -1.19
    与此同时
    -1.12
    Nép
    -1.08
    定食
    -1.08
    さらに
    -1.06
    新的
    -1.05
     in
    -1.05
    calciatore
    -1.04
    POSITIVE LOGITS
    のでしょう
    1.36
     spada
    1.20
    しば
    1.19
    様な
    1.13
     cojín
    1.11
     loro
    1.10
     northwest
    1.09
    ITHER
    1.09
     northeast
    1.09
     côtés
    1.09
    Activations Density 0.002%

    No Known Activations