© 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. 206451
    Prev
    Next
    INDEX
    Explanations

    set of followed by specific words

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

    lists and phrases

    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
    >?,
    0.50
     에게
    0.50
     neutralized
    0.49
     данной
    0.48
     собственно
    0.48
    }$&$
    0.47
     सेलिब्र
    0.47
     небольшой
    0.46
    >≤</
    0.45
    ене
    0.44
    POSITIVE LOGITS
    ור
    0.56
    ও
    0.51
    বার
    0.50
    vasive
    0.50
    رد
    0.47
    바
    0.46
    اب
    0.46
    ポート
    0.46
    ር
    0.46
    מס
    0.46
    Activations Density 0.002%

    No Known Activations