© 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. 160075
    Prev
    Next
    INDEX
    Explanations

    foreign language words and phrases

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

    insertion, negotiation, from

    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
    .
    0.50
    3
    0.47
    i
    0.47
     They
    0.46
    0.45
     The
    0.44
    都
    0.44
    :
    0.44
    They
    0.43
    ?"
    0.43
    POSITIVE LOGITS
     रिमाइंडर
    0.53
    hemian
    0.51
     කිරීමට
    0.50
     लौटने
    0.49
     장면
    0.48
    ப்பிர
    0.48
     equilibration
    0.48
    항
    0.48
     শতাব্দীর
    0.47
     음악
    0.47
    Activations Density 0.001%

    No Known Activations