© 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. 143371
    Prev
    Next
    INDEX
    Explanations

    describing qualities and outcomes

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

    bank, if, 2, force, string

    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
    По
    0.53
    Фран
    0.51
     небе
    0.49
     ядра
    0.48
    у
    0.48
    тру
    0.47
     процеду
    0.47
    же
    0.46
    Как
    0.46
    и
    0.46
    POSITIVE LOGITS
     \|
    0.49
    嫂
    0.46
     dupatta
    0.45
     stär
    0.45
    隍
    0.43
     potholes
    0.43
    Chef
    0.42
    college
    0.42
     Choi
    0.42
    sees
    0.41
    Activations Density 0.000%

    No Known Activations