© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111709
    Prev
    Next
    INDEX
    Explanations

    guide to achieving outcomes

    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_40_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
    φαν
    0.42
     nessun
    0.41
     können
    0.40
    ূল্য
    0.40
     või
    0.39
     erhältlich
    0.39
    或
    0.39
    ጬ
    0.38
     koriste
    0.38
    დება
    0.37
    POSITIVE LOGITS
     posteriorly
    0.45
     persists
    0.44
     مختصر
    0.42
     removal
    0.41
     opposites
    0.40
     history
    0.39
     Pennsylvania
    0.39
     persistence
    0.39
     continued
    0.38
     persist
    0.38
    Activations Density 0.002%

    No Known Activations