© 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. 10-GEMMASCOPE-RES-131K
    7. 8235
    Prev
    Next
    INDEX
    Explanations

    reflexive pronoun itselfto itself

    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_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
    蚡
    -2.91
     and
    -2.77
    聽到
    -2.66
     offizielle
    -2.53
     klassische
    -2.45
    0
    -2.41
     blaue
    -2.36
     zentrale
    -2.34
     vollständige
    -2.33
     Jahrgang
    -2.27
    POSITIVE LOGITS
     It
    3.86
     There
    2.84
     adalah
    2.67
    ⡯
    2.63
    )，
    2.56
     älskar
    2.50
    there
    2.48
    n
    2.45
    最重要的
    2.44
     swoją
    2.42
    Activations Density 0.007%

    No Known Activations