© 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. 40-GEMMASCOPE-2-RES-262K
    7. 213659
    Prev
    Next
    INDEX
    Explanations

    annot, mask

    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
    రుపు
    0.39
    大学
    0.38
    CONF
    0.38
     brimming
    0.38
    Tiempo
    0.38
    餑
    0.38
    ೮
    0.37
    िवा
    0.37
    期間
    0.37
    however
    0.37
    POSITIVE LOGITS
     Mask
    0.49
     c
    0.45
    annot
    0.45
     annot
    0.45
     Annot
    0.43
     mask
    0.42
     De
    0.42
    toml
    0.40
     Pool
    0.40
    mask
    0.39
    Activations Density 0.000%

    No Known Activations