© 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. 128854
    Prev
    Next
    INDEX
    Explanations

    data plan

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

    language and diverse topics

    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
     centri
    0.45
     carefully
    0.45
     compression
    0.44
     in
    0.44
     it
    0.43
    Hint
    0.43
    د
    0.42
     efforts
    0.42
     \
    0.40
     =
    0.40
    POSITIVE LOGITS
     полез
    0.53
     nayo
    0.51
    байд
    0.51
    ज़्
    0.50
    らない
    0.50
    নারায়ণ
    0.49
    ナー
    0.49
    ynı
    0.48
     რომელი
    0.48
     झाल्यानंतर
    0.48
    Activations Density 0.000%

    No Known Activations