© 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. 40-GEMMASCOPE-2-RES-262K
    7. 192666
    Prev
    Next
    INDEX
    Explanations

    Ginger ale, ginger snaps, ginger gold

    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
    ensen
    0.40
    📀
    0.37
     Rada
    0.37
     potassium
    0.37
    ewood
    0.37
    徑
    0.37
    propylene
    0.36
    uation
    0.36
    ensch
    0.36
     успеха
    0.36
    POSITIVE LOGITS
    bread
    0.42
    ാ
    0.40
     распространен
    0.40
     broadly
    0.39
    ূপ
    0.38
     lecz
    0.38
    葺
    0.38
    濤
    0.38
     ale
    0.38
     experimenting
    0.38
    Activations Density 0.002%

    No Known Activations