© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 68597
    Prev
    Next
    INDEX
    Explanations

    American, southern, contagious

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

    step by step

    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
     ㅣ
    0.55
     Huerta
    0.54
    ,_
    0.52
     piezo
    0.51
     apoptosis
    0.50
     FUR
    0.49
    3
    0.48
     quies
    0.48
     inmediata
    0.47
     松
    0.47
    POSITIVE LOGITS
    我們
    0.43
    ён
    0.43
    زي
    0.43
    американ
    0.43
    আমরা
    0.42
    了一种
    0.42
    Here
    0.42
    زب
    0.41
     અમે
    0.41
    वे
    0.40
    Activations Density 0.000%

    No Known Activations