© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2340
    Prev
    Next
    INDEX
    Explanations

    model

    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
    ików
    0.43
    ullar
    0.43
    ی
    0.43
    um
    0.43
    itation
    0.43
    ları
    0.43
    n
    0.42
    sk
    0.42
    ühlt
    0.42
     escrito
    0.41
    POSITIVE LOGITS
     그의
    0.42
    ﺤ
    0.39
    阕
    0.38
    HLER
    0.37
     getUsersBy
    0.36
     गणना
    0.35
     유
    0.34
    、“
    0.34
    ייה
    0.34
    흠
    0.34
    Activations Density 0.059%

    No Known Activations