© 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. 95245
    Prev
    Next
    INDEX
    Explanations

    on the, live and, pass the

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

    scientific concepts and terms

    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
     Unicorn
    0.45
     油
    0.42
    OF
    0.40
    -
    0.40
     skin
    0.39
     pour
    0.39
     Veneto
    0.39
     Instituto
    0.38
     of
    0.38
     Closer
    0.38
    POSITIVE LOGITS
    ভাই
    0.48
     происходит
    0.47
    い
    0.47
    下来的
    0.46
     લઇ
    0.46
    ⬮
    0.46
    ப்பழ
    0.45
    ফল
    0.45
     আছে
    0.45
    াশ
    0.44
    Activations Density 0.000%

    No Known Activations