© 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. 36755
    Prev
    Next
    INDEX
    Explanations

    prefix followed by specific word type

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

    chronological contradictions and instructions

    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
     deri
    0.49
     fortification
    0.47
     derece
    0.47
     signification
    0.47
    崬
    0.47
     directement
    0.46
     sezione
    0.46
     Vedi
    0.46
     ማስ
    0.45
     dirige
    0.45
    POSITIVE LOGITS
    ourd
    0.52
    bu
    0.52
    这两
    0.49
    职
    0.48
    hk
    0.47
    horm
    0.46
    iót
    0.46
    号
    0.46
    brit
    0.45
    两年
    0.45
    Activations Density 0.000%

    No Known Activations