© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 233330
    Prev
    Next
    INDEX
    Explanations

    international place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     asociaciones
    0.51
     leng
    0.48
     kemampuan
    0.47
    kent
    0.47
     condos
    0.46
     sanciones
    0.46
    enges
    0.46
    掂
    0.46
     Kain
    0.45
    antiene
    0.45
    POSITIVE LOGITS
    Natal
    0.52
    IES
    0.51
    Yea
    0.51
    Flux
    0.50
    Jou
    0.50
    Qatar
    0.49
    Jay
    0.48
    Quem
    0.48
    Gul
    0.48
    Espagne
    0.48
    Activations Density 0.000%

    No Known Activations