© 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. 1554
    Prev
    Next
    INDEX
    Explanations

    has + past participle

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

    have been / past participle

    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
    0
    0.24
     如果
    0.23
     أو
    0.21
     rotors
    0.20
     或
    0.20
     او
    0.19
    िस
    0.19
     if
    0.19
     when
    0.19
     olefins
    0.19
    POSITIVE LOGITS
     been
    0.54
    been
    0.46
     BEEN
    0.42
     Been
    0.39
    Been
    0.36
     become
    0.29
     fått
    0.27
     got
    0.27
    become
    0.27
     ollut
    0.27
    Activations Density 0.732%

    No Known Activations