© 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. 212894
    Prev
    Next
    INDEX
    Explanations

    save time and money

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

    endless opportunities, several facts

    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
    ८
    0.60
    Radiux
    0.47
     തി
    0.46
    𝔯
    0.46
    ştir
    0.45
    withdraw
    0.45
    नीकरण
    0.43
     hemicontinuous
    0.43
    월
    0.43
    曷
    0.43
    POSITIVE LOGITS
     voltages
    0.51
     associations
    0.48
     on
    0.47
     inbound
    0.46
    es
    0.45
    associations
    0.45
    axes
    0.44
     ballots
    0.44
     delivered
    0.43
     less
    0.42
    Activations Density 0.000%

    No Known Activations