© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9326
    Prev
    Next
    INDEX
    Explanations

    AI, OpenAI, NASA, Google, research sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    akos
    0.91
    佰
    0.90
    atypes
    0.86
    acs
    0.86
    ansh
    0.85
    acos
    0.85
     necessitating
    0.85
     substantially
    0.84
     $\|\
    0.83
    ያስ
    0.82
    POSITIVE LOGITS
     टिश
    0.89
    ++];
    0.87
     tissue
    0.86
    ξει
    0.85
     राठ
    0.84
     retir
    0.84
    ίνουν
    0.83
    tissue
    0.82
     метал
    0.81
    idina
    0.81
    Activations Density 0.030%

    No Known Activations