© 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. 16-GEMMASCOPE-2-RES-262K
    7. 118850
    Prev
    Next
    INDEX
    Explanations

    Netanyahu, NetEnt slots, Rutte

    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_16_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
    5
    0.89
    de
    0.80
    AT
    0.73
    𝓲
    0.71
    জিন
    0.67
    9
    0.66
    OCUS
    0.63
    you
    0.60
    4
    0.60
    Application
    0.59
    POSITIVE LOGITS
    ור
    0.72
    ens
    0.66
    ார்
    0.64
     unremarkable
    0.60
    oon
    0.55
     unequal
    0.54
     or
    0.54
    та
    0.54
    aremos
    0.53
    の結果
    0.53
    Activations Density 0.000%

    No Known Activations