© 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. 72364
    Prev
    Next
    INDEX
    Explanations

    prepositions and common verbs

    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
     and
    -1.63
     also
    -1.63
     Gesetze
    -1.27
    djang
    -1.16
    ↵↵
    -1.15
     alcune
    -1.13
     laws
    -1.13
     effects
    -1.13
     largely
    -1.09
    câ
    -1.07
    POSITIVE LOGITS
    licopter
    1.70
    ㅂ
    1.40
    וּ
    1.29
     التالي
    1.27
    ➀
    1.27
     söyl
    1.26
    ඨ
    1.26
     söyledi
    1.26
    Lieferumfang
    1.25
    まずは
    1.20
    Activations Density 0.089%

    No Known Activations