© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113581
    Prev
    Next
    INDEX
    Explanations

    what has changed

    np_acts-logits-general · gemini-2.5-flash-lite

    the specific word “changed.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    sorry
    -1.53
    A
    -1.45
     различ
    -1.36
    ときに
    -1.35
     recent
    -1.34
    DESCRIPCIÓN
    -1.33
    UrlHelper
    -1.27
    
    -1.26
     letzter
    -1.25
     différentes
    -1.24
    POSITIVE LOGITS
     this
    2.00
     in
    1.50
     they
    1.48
     these
    1.46
     for
    1.46
     that
    1.44
     или
    1.43
    我会
    1.40
     their
    1.38
    极了
    1.36
    Activations Density 0.018%

    No Known Activations