© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 259657
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    駒
    0.45
    ități
    0.44
    ak
    0.43
     grits
    0.42
    ▸
    0.41
     delimiters
    0.40
    いま
    0.40
     disorientation
    0.40
    含ま
    0.40
    リ
    0.40
    POSITIVE LOGITS
    BF
    0.53
    GF
    0.48
    nasium
    0.45
    ঞ্জার
    0.45
    नेशनल
    0.43
    SalesReport
    0.43
     هيكون
    0.43
     BF
    0.42
     lezione
    0.42
    NX
    0.42
    Activations Density 0.002%

    No Known Activations