© 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. 39192
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    numbers or categories

    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
     शुगर
    0.45
     înt
    0.44
    ğmen
    0.43
     ఇండి
    0.42
    ISING
    0.41
     hik
    0.41
    誐
    0.41
    GALAD
    0.40
    uluk
    0.40
    上限
    0.40
    POSITIVE LOGITS
    wxr
    0.39
    ,...,
    0.39
    he
    0.38
     Different
    0.38
     crise
    0.38
    ↵↵
    0.38
    sw
    0.37
    ↵
    0.36
     Install
    0.36
    base
    0.36
    Activations Density 0.002%

    No Known Activations