© 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. 59334
    Prev
    Next
    INDEX
    Explanations

    numbers and specific topics

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

    specific examples and descriptions

    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
    лаго
    0.46
    म्या
    0.45
    нике
    0.43
    offsets
    0.43
    𝘆
    0.43
    your
    0.42
    nw
    0.42
    менте
    0.42
    ън
    0.42
    ಬೇವಿನ
    0.42
    POSITIVE LOGITS
     شك
    0.48
    িল
    0.45
     تك
    0.45
     সম্ভাব
    0.44
     ź
    0.43
    共产
    0.43
    Archae
    0.42
     ყველ
    0.42
     libertà
    0.42
     updateConfirm
    0.41
    Activations Density 0.000%

    No Known Activations