© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5034
    Prev
    Next
    INDEX
    Explanations

    new batch or WebSocket

    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_12_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
     גם
    2.35
    決して
    2.33
     každý
    2.31
    떼
    2.18
    lüğü
    2.17
    taker
    2.16
     établir
    2.16
    删
    2.14
    链路
    2.09
     uży
    2.09
    POSITIVE LOGITS
     Expos
    1.11
     marketable
    1.08
     Resources
    1.03
     Expo
    1.00
    èles
    0.96
    膺
    0.95
     homologous
    0.94
    estries
    0.93
     Pools
    0.93
     obedient
    0.92
    Activations Density 0.000%

    No Known Activations