© 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-16K
    7. 5434
    Prev
    Next
    INDEX
    Explanations

    printing output and code structure

    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_16k_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
    north
    0.44
    t
    0.42
    elink
    0.41
     <
    0.38
    aci
    0.37
    anthropy
    0.36
    ijing
    0.36
    outines
    0.36
     withered
    0.36
    northern
    0.35
    POSITIVE LOGITS
    幔
    0.53
    레
    0.46
     아래
    0.45
    隔
    0.44
     आल्सो
    0.43
    셈
    0.43
     гео
    0.42
     ಕೇಳ
    0.42
     방식으로
    0.42
     stellte
    0.42
    Activations Density 0.177%

    No Known Activations