© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2191
    Prev
    Next
    INDEX
    Explanations

    mountains, hills, and peaks

    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_9_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
    뭔
    1.88
    當
    1.74
    squareup
    1.70
    笞
    1.65
    സ്ഥ
    1.62
    스로
    1.60
    م
    1.59
    aqua
    1.57
    きました
    1.53
    idler
    1.52
    POSITIVE LOGITS
     mountain
    2.51
     gunung
    2.40
     mountaine
    2.31
    🏔
    2.24
     mountains
    2.20
    Hiking
    2.19
     foothills
    2.19
     hiking
    2.18
    Mountains
    2.17
     Himalayas
    2.10
    Activations Density 0.347%

    No Known Activations