© 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. 41546
    Prev
    Next
    INDEX
    Explanations

    start of sentences or quoted phrases

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

    code and explanations

    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
     trúc
    0.45
     بسم
    0.43
    缟
    0.43
    руппа
    0.41
     âmbito
    0.41
    ována
    0.40
    числя
    0.39
    RENCE
    0.39
     Министерство
    0.39
    0.39
    POSITIVE LOGITS
     مذکور
    0.48
    ]<<"
    0.43
    4
    0.41
    ]
    0.40
    他还
    0.39
    3
    0.39
    <eos>
    0.38
     aforementioned
    0.37
    "},
    0.37
    win
    0.36
    Activations Density 0.573%

    No Known Activations