© 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. 34369
    Prev
    Next
    INDEX
    Explanations

    words of endearment and praise

    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
     Ubicación
    -1.41
    ᅲ
    -1.39
    ַּ
    -1.31
     empezaron
    -1.31
    bánh
    -1.30
     toekomst
    -1.30
    Liet
    -1.28
    ִּ
    -1.26
     podéis
    -1.23
    instagram
    -1.22
    POSITIVE LOGITS
     this
    1.71
     also
    1.23
     very
    1.16
     again
    1.02
     still
    1.00
     опять
    1.00
    tová
    0.99
     rather
    0.98
    <mask>
    0.97
     showing
    0.96
    Activations Density 0.009%

    No Known Activations