© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99686
    Prev
    Next
    INDEX
    Explanations

    expressing regret or misfortune

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </sub>
    -2.36
    着他
    -2.25
     mantenido
    -2.22
    тися
    -2.17
    玧
    -2.11
    臆
    -2.09
    ).
    -2.05
    uttori
    -2.00
    ванием
    -1.99
     edgy
    -1.98
    POSITIVE LOGITS
    which
    4.31
    with
    3.03
    the
    3.00
    这里
    2.97
    of
    2.89
    that
    2.84
    their
    2.81
    these
    2.77
    how
    2.73
    to
    2.72
    Activations Density 0.004%

    No Known Activations