© 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. 70019
    Prev
    Next
    INDEX
    Explanations

    following items

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

    evaluating and ranking

    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
    ერს
    0.56
    thing
    0.48
    製
    0.48
    *}\
    0.44
    Ｌ
    0.43
    事で
    0.43
    kého
    0.42
    ○
    0.42
    ク
    0.42
    datasets
    0.41
    POSITIVE LOGITS
     انتہائی
    0.50
     aşağı
    0.49
     aşağıdaki
    0.47
     निम्न
    0.46
     kardeş
    0.46
     tidigare
    0.43
    ँकि
    0.42
     kock
    0.42
     অন্যান্য
    0.42
     eerder
    0.42
    Activations Density 0.001%

    No Known Activations