© 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. 13384
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases

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

    GGML

    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
     easier
    0.47
    ,
    0.47
    ),
    0.46
    vu
    0.42
    조
    0.41
    )…
    0.41
     Bos
    0.40
    )
    0.40
    )[
    0.40
     accessible
    0.40
    POSITIVE LOGITS
    Roaming
    0.53
    ordnung
    0.45
     सीएचसी
    0.45
    strukt
    0.44
    玴
    0.43
    Mead
    0.43
    laughs
    0.43
    prnewswire
    0.43
    Brands
    0.43
    獷
    0.42
    Activations Density 0.000%

    No Known Activations