© 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. 31-GEMMASCOPE-2-RES-262K
    7. 29274
    Prev
    Next
    INDEX
    Explanations

    px

    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
     %>%
    0.48
     Lega
    0.42
    edil
    0.41
     bag
    0.40
     pictogram
    0.39
    luc
    0.38
     relic
    0.38
    𝓾
    0.38
    δος
    0.37
    काया
    0.37
    POSITIVE LOGITS
     vicino
    0.46
     samma
    0.40
     Ć
    0.40
     their
    0.39
     samego
    0.38
     mesma
    0.38
     samme
    0.38
     closeup
    0.38
     colorless
    0.38
    았습니다
    0.38
    Activations Density 0.011%

    No Known Activations