© 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. 109356
    Prev
    Next
    INDEX
    Explanations

    create video

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

    many potential targets

    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
     dãy
    0.52
     uncles
    0.49
     kuts
    0.48
     urs
    0.46
     gode
    0.46
     são
    0.45
     ẹ
    0.45
     kut
    0.44
     két
    0.44
     strictement
    0.44
    POSITIVE LOGITS
    簿
    0.47
    お金
    0.46
    זי
    0.45
    multline
    0.45
     اکنون
    0.45
    人と
    0.44
    تو
    0.43
    就能
    0.43
    midd
    0.43
     SECOND
    0.43
    Activations Density 0.000%

    No Known Activations