© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6111
    Prev
    Next
    INDEX
    Explanations

    mountains, forests, woods, jungles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    connector
    1.11
     monet
    1.06
     Mengen
    1.03
     Nautical
    1.01
     mercantil
    1.01
     pleasurable
    0.96
    율
    0.96
     caut
    0.95
     pot
    0.94
     vessel
    0.93
    POSITIVE LOGITS
    tops
    2.36
    巔
    2.20
    acharya
    2.20
     nacionais
    1.94
    巅
    1.89
    ocks
    1.84
    トップ
    1.84
    ücks
    1.83
    énie
    1.82
    omel
    1.81
    Activations Density 0.079%

    No Known Activations