© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5442
    Prev
    Next
    INDEX
    Explanations

    river

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ف
    1.40
    ش
    1.20
    𝘁
    1.16
    iz
    1.15
    c
    1.13
    t
    1.12
    İM
    1.09
    क
    1.08
    ж
    1.08
    ز
    1.08
    POSITIVE LOGITS
     rivers
    1.67
    河流
    1.67
     sungai
    1.59
     tributaries
    1.55
    8
    1.48
     river
    1.46
     rapids
    1.45
    River
    1.41
     rivulet
    1.41
     rafting
    1.39
    Activations Density 0.043%

    No Known Activations