© 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. 34-GEMMASCOPE-RES-131K
    7. 30324
    Prev
    Next
    INDEX
    Explanations

    contralateral or opposite

    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_34/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
    ख़
    -0.74
    divia
    -0.74
    了吧
    -0.71
     både
    -0.70
    imar
    -0.69
    гиоз
    -0.69
    рость
    -0.68
    ATTACHMENT
    -0.68
    ք
    -0.68
    codegen
    -0.68
    POSITIVE LOGITS
     opposite
    7.53
    opposite
    6.13
    Opposite
    5.53
     Opposite
    5.50
     противополо
    4.47
     opposing
    4.38
     opposites
    3.59
    反対
    3.17
     gegenüber
    3.16
     opposed
    3.13
    Activations Density 0.183%

    No Known Activations