© 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-16K
    7. 13190
    Prev
    Next
    INDEX
    Explanations

    words ending in "ion"

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

    different types of text introductions

    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_16k_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
     I
    0.93
    ни
    0.79
    </strong>
    0.76
    ela
    0.71
    ora
    0.70
    3
    0.70
    0
    0.69
    را
    0.68
    ٣
    0.68
    后果
    0.68
    POSITIVE LOGITS
    a
    1.23
    ه
    1.20
    ה
    1.13
    는
    1.00
    া
    0.98
    াং
    0.95
    هي
    0.90
    ר
    0.85
    ن
    0.84
    മ
    0.83
    Activations Density 0.000%

    No Known Activations