© 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. 126905
    Prev
    Next
    INDEX
    Explanations

    having said that

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

    configuration or troubleshooting

    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
     lundi
    0.49
     defesa
    0.49
    dine
    0.49
    嗰
    0.49
    wann
    0.48
     पाण
    0.47
    tus
    0.46
    mob
    0.45
    daftar
    0.45
    রোপ
    0.45
    POSITIVE LOGITS
     보험
    0.48
     শাস্তি
    0.45
    řich
    0.45
     آموزش
    0.43
     다른
    0.42
     নির্যা
    0.42
     เหมาะ
    0.41
     되었
    0.41
     $\|\
    0.40
     교육
    0.40
    Activations Density 0.001%

    No Known Activations