© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90998
    Prev
    Next
    INDEX
    Explanations

    following verbs or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Unfortunately
    0.46
     distracting
    0.46
    無需
    0.46
     ಎಲ್ಲಾ
    0.45
     confusing
    0.44
     informative
    0.43
     confusion
    0.43
     ਬ
    0.43
    alassemia
    0.41
    Confusion
    0.40
    POSITIVE LOGITS
     rãi
    0.48
     développement
    0.46
     развитии
    0.44
     alrededores
    0.43
     privilegi
    0.43
     động
    0.43
     временем
    0.43
     повы
    0.42
     cierta
    0.42
     politiques
    0.42
    Activations Density 0.004%

    No Known Activations