© 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. 77716
    Prev
    Next
    INDEX
    Explanations

    accomplish then

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

    create unsafe, see seen, clearly seen

    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
     Happiness
    0.44
    আমার
    0.42
    UILLER
    0.42
    ുമോ
    0.42
    宿
    0.42
    happiness
    0.42
    പ്പുറ
    0.41
    0.41
     алыңыз
    0.40
     alamat
    0.39
    POSITIVE LOGITS
    ்ப்ப
    0.51
     يُ
    0.49
    ⴹ
    0.49
     식이
    0.48
    이가
    0.48
     훨
    0.47
     становится
    0.47
    ⵔ
    0.47
     السيد
    0.46
    ⤠
    0.46
    Activations Density 0.000%

    No Known Activations