© 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. 128378
    Prev
    Next
    INDEX
    Explanations

    common nouns following the

    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
     également
    -1.31
     perfección
    -1.20
    werfen
    -1.19
     DIFFERENT
    -1.17
     CERTAIN
    -1.13
    當時
    -1.12
    Kemudian
    -1.10
     みた
    -1.09
     arrêter
    -1.09
    Kedves
    -1.09
    POSITIVE LOGITS
     ones
    2.61
     one
    1.65
     quelli
    1.47
     ability
    1.42
     obvious
    1.41
    Those
    1.35
    jenigen
    1.35
     منها
    1.35
     outono
    1.34
    They
    1.30
    Activations Density 0.068%

    No Known Activations