© 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. 110390
    Prev
    Next
    INDEX
    Explanations

    countdown lists

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

    core or current

    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
     too
    0.47
    ിത്ര
    0.46
     warning
    0.44
    1
    0.44
    最新的
    0.44
    ട്ടെ
    0.43
     cutting
    0.43
     popping
    0.42
     discriminate
    0.42
     CANT
    0.42
    POSITIVE LOGITS
    屶
    0.54
    境界層
    0.52
     بسيط
    0.52
    ugian
    0.51
    ਨ
    0.50
    на
    0.47
     تھیں
    0.47
     условиях
    0.47
    ahun
    0.46
     акты
    0.46
    Activations Density 0.001%

    No Known Activations