© 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. 157833
    Prev
    Next
    INDEX
    Explanations

    PML political context

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

    classification and examples

    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
     segmentation
    0.52
    ふ
    0.47
     অবস্থানের
    0.46
    ici
    0.44
    esting
    0.44
    če
    0.43
    itional
    0.42
    ichten
    0.41
     teg
    0.41
    ungen
    0.41
    POSITIVE LOGITS
    ুল
    0.52
    ότε
    0.51
    ت
    0.51
    سه
    0.50
    崞
    0.46
    ون
    0.46
    ről
    0.46
     Име
    0.46
    ról
    0.45
    тың
    0.45
    Activations Density 0.002%

    No Known Activations