© 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. 231973
    Prev
    Next
    INDEX
    Explanations

    fine tip

    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
    রূপ
    0.57
    נג
    0.52
    רה
    0.51
    ברי
    0.50
    م
    0.49
    וד
    0.48
    مود
    0.48
    న్స్
    0.48
    უს
    0.46
     に対
    0.46
    POSITIVE LOGITS
     metallurgy
    0.48
     biochemistry
    0.48
     asymmetries
    0.47
     imposible
    0.47
     gaps
    0.46
     esperienza
    0.46
    子が
    0.46
     phylogeny
    0.46
    痍
    0.46
     sclerosis
    0.44
    Activations Density 0.001%

    No Known Activations