© 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. 72356
    Prev
    Next
    INDEX
    Explanations

    future tense auxiliary verbs

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

    workforce analytics and optimization

    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
     endeavoured
    0.48
     corporates
    0.48
     unfold
    0.46
    ವ
    0.46
     கட்டமை
    0.46
    場
    0.46
    にした
    0.45
    Commissioner
    0.45
     quieren
    0.45
    issuer
    0.44
    POSITIVE LOGITS
     Decrease
    0.45
     D
    0.42
     Kosten
    0.41
     Dollars
    0.40
     Pall
    0.40
     Orn
    0.38
     nélkül
    0.38
     sämt
    0.38
     Train
    0.37
     сни
    0.37
    Activations Density 0.006%

    No Known Activations