© 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. 110874
    Prev
    Next
    INDEX
    Explanations

    phrases like "already had" or "means eliminating"

    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
     in
    0.50
     ernst
    0.43
     prij
    0.43
     matri
    0.42
     liberdade
    0.42
     persuasion
    0.41
     preços
    0.41
    鑄
    0.41
     در
    0.40
     primal
    0.40
    POSITIVE LOGITS
    amp
    0.50
    тово
    0.48
    (`./
    0.44
    ómo
    0.44
     Сури
    0.43
    ants
    0.43
     Sur
    0.42
    uerdo
    0.41
    ianas
    0.41
    ```
    0.41
    Activations Density 0.007%

    No Known Activations