© 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. 146183
    Prev
    Next
    INDEX
    Explanations

    numbers, realization, according, flights, energy, instructions, User, Fili

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

    some ideas, notes, questions

    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
    ankt
    0.45
    aruhi
    0.45
    ним
    0.44
    ofield
    0.44
    oksi
    0.43
     वनडे
    0.43
    estä
    0.43
    ]
    0.43
     Street
    0.43
     शर्त
    0.42
    POSITIVE LOGITS
    څ
    0.46
    욜
    0.44
     پرته
    0.43
     personalize
    0.43
    트를
    0.43
     cách
    0.42
    VITY
    0.42
     می‌توانید
    0.42
     manière
    0.42
    جام
    0.42
    Activations Density 0.000%

    No Known Activations