© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128233
    Prev
    Next
    INDEX
    Explanations

    Indonesian and Portuguese suffixes/words like -nya and fonctionner/aparentemente

    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
    ꪔ
    -2.69
    鷓
    -2.61
     and
    -2.59
    骘
    -2.53
     CAMPBELL
    -2.45
    -2.44
    耵
    -2.44
    硨
    -2.42
    ᥬ
    -2.42
    ;;)
    -2.41
    POSITIVE LOGITS
     It
    3.19
    )
    2.97
    </h2>
    2.86
    n
    2.58
    In
    2.53
    …
    2.53
    _
    2.47
    when
    2.41
    With
    2.33
    The
    2.30
    Activations Density 0.001%

    No Known Activations