© 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. 214696
    Prev
    Next
    INDEX
    Explanations

    Vertex AI and compute

    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
    ŝ
    0.40
    籠
    0.39
    மோ
    0.37
    鈉
    0.37
    rà
    0.37
    𝗥
    0.36
     ग्रहण
    0.36
     dialects
    0.36
    rät
    0.36
     imperative
    0.35
    POSITIVE LOGITS
    BeerItem
    0.44
     Minim
    0.39
    ייש
    0.38
    Feature
    0.37
    টর
    0.37
    LineEdit
    0.37
    layoutWidget
    0.37
    亳
    0.37
    Pool
    0.37
    childNodes
    0.37
    Activations Density 0.012%

    No Known Activations