© 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. 96350
    Prev
    Next
    INDEX
    Explanations

    disclosures, provided, shares

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

    theoretical justification

    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
    arów
    0.59
     іх
    0.57
     민
    0.54
     vijj
    0.53
     आरमारा
    0.52
     円
    0.52
     jīn
    0.51
     ハ
    0.51
     항
    0.50
     プラス
    0.50
    POSITIVE LOGITS
    0.52
    zhang
    0.45
     disclosures
    0.43
    مع
    0.43
     relativity
    0.41
    context
    0.41
     Disclosure
    0.41
    م
    0.41
    Heat
    0.40
    WB
    0.40
    Activations Density 0.004%

    No Known Activations