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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10288
    Prev
    Next
    INDEX
    Explanations

    rivers and their flows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     antena
    0.88
    鹌
    0.86
    squares
    0.85
     mushrooms
    0.84
     squares
    0.83
     PATCH
    0.83
     patch
    0.82
     kvadrat
    0.82
    布団
    0.82
    蜂
    0.82
    POSITIVE LOGITS
     river
    2.61
     River
    2.40
     rivers
    2.22
    River
    2.21
     rivière
    2.13
     waterway
    2.06
     Rivers
    2.03
    river
    2.02
     downstream
    2.01
     fiume
    1.99
    Activations Density 0.334%

    No Known Activations