© 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. 46686
    Prev
    Next
    INDEX
    Explanations

    few simple, the next

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

    filename, rename, import

    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
    вия
    0.51
    вите
    0.48
    পুর
    0.47
    vit
    0.47
     Arias
    0.43
    ีย
    0.43
    屈
    0.43
    μου
    0.42
    Ss
    0.42
    <unused105>
    0.42
    POSITIVE LOGITS
     rename
    0.53
     renaming
    0.50
     नर
    0.46
     नतीजा
    0.46
    deserialize
    0.46
     श्रमिक
    0.44
     تبدیل
    0.44
     сюжет
    0.44
    িত্যক্ত
    0.44
     channeling
    0.43
    Activations Density 0.000%

    No Known Activations