© 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. 67609
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and personal accounts

    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
     ranting
    -1.41
     nyní
    -1.26
     currently
    -1.23
    jdź
    -1.20
    ulación
    -1.17
     labd
    -1.16
    っぱり
    -1.16
     =
    -1.09
     infuri
    -1.09
     actualmente
    -1.07
    POSITIVE LOGITS
     metod
    1.24
     three
    1.23
     them
    1.17
     with
    1.16
     deseas
    1.13
     erreur
    1.13
     during
    1.12
     fece
    1.11
     one
    1.09
    瘠
    1.09
    Activations Density 0.064%

    No Known Activations