© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112652
    Prev
    Next
    INDEX
    Explanations

    The relationship between words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     región
    0.52
     District
    0.50
     district
    0.47
    त
    0.47
     febbraio
    0.46
    ت
    0.46
     winter
    0.46
     kat
    0.45
     petrol
    0.44
     viet
    0.44
    POSITIVE LOGITS
     お客様
    0.45
    诰
    0.45
    aboutme
    0.45
     יותר
    0.44
     δυνα
    0.44
     כת
    0.43
    のことを
    0.42
    の関係
    0.41
    အတွ
    0.41
    _{+}$
    0.41
    Activations Density 0.005%

    No Known Activations