© 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. 76830
    Prev
    Next
    INDEX
    Explanations

    small & neighborhoods

    np_acts-logits-general · gemini-2.5-flash-lite

    small words or neighborhoods

    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
    的同时
    0.44
     Elements
    0.40
    нечно
    0.40
    上的
    0.40
     Welding
    0.40
    军
    0.40
    rawy
    0.39
    纰
    0.39
    踺
    0.39
    跗
    0.39
    POSITIVE LOGITS
     neighborhoods
    0.47
     abaste
    0.45
     pequeño
    0.44
     små
    0.43
     pequeña
    0.42
     bairro
    0.42
     piccoli
    0.42
     kecil
    0.41
     biomark
    0.41
     μικ
    0.41
    Activations Density 0.004%

    No Known Activations