© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 960
    Prev
    Next
    INDEX
    Explanations

    was/had/be + past participle

    np_acts-logits-general · gemini-2.5-flash-lite

    Personalization, job opportunity, responding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    いろいろ
    0.47
    笕
    0.46
    总之
    0.46
     한다는
    0.46
     예상
    0.45
     አንዳንድ
    0.44
    ק
    0.44
    ｛
    0.44
    mittal
    0.44
    各種
    0.44
    POSITIVE LOGITS
     premiere
    0.57
     mosque
    0.55
    *.
    0.52
     monumental
    0.52
     frontline
    0.51
     serviced
    0.50
     premieres
    0.49
     immediately
    0.49
     zoo
    0.48
     parque
    0.48
    Activations Density 0.000%

    No Known Activations