© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37929
    Prev
    Next
    INDEX
    Explanations

    ask, drive, done, out

    np_acts-logits-general · gemini-2.5-flash-lite

    known issues or defects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     barcodes
    0.42
    automobile
    0.41
    ڨ
    0.39
    clientX
    0.39
    trim
    0.38
    ót
    0.38
    трим
    0.38
     TRUST
    0.38
    띤
    0.37
    prices
    0.37
    POSITIVE LOGITS
     Ask
    0.47
     ask
    0.40
     chiesto
    0.40
     Jesu
    0.39
     meminta
    0.39
     sukham
    0.39
     penyakit
    0.38
     Democrats
    0.38
     Kesehatan
    0.38
     kalau
    0.38
    Activations Density 0.017%

    No Known Activations