© 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. 7664
    Prev
    Next
    INDEX
    Explanations

    also / أيضًا / גם

    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
     Bemerkungen
    -1.70
     alcun
    -1.63
     indispens
    -1.59
    鐃
    -1.59
     necesar
    -1.52
     lavorare
    -1.45
    ኧ
    -1.45
     nasce
    -1.40
    enschutzer
    -1.39
     escuchado
    -1.39
    POSITIVE LOGITS
     \
    1.64
     גם
    1.57
     أيضًا
    1.47
    着他
    1.46
    mathrm
    1.41
     also
    1.40
    了一会儿
    1.38
    xffffff
    1.37
    着她
    1.36
     usually
    1.34
    Activations Density 0.039%

    No Known Activations