© 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. 172730
    Prev
    Next
    INDEX
    Explanations

    imported polio, Porcelain Repair, peer reviewed, liberal coat, transatlantic communication

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

    My followed by webpage elements

    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
     وہ
    0.44
     একসঙ্গে
    0.42
     ясно
    0.41
    ೀಯ
    0.40
     који
    0.40
     мог
    0.39
    ---->
    0.39
     能
    0.38
     వెంట
    0.38
    ্যেষ্ঠ
    0.38
    POSITIVE LOGITS
    riko
    0.46
    ’
    0.46
     Tav
    0.45
     تاس
    0.45
     sortir
    0.44
     Individ
    0.44
     tribunals
    0.44
     Flamingo
    0.43
     Tada
    0.43
    teras
    0.43
    Activations Density 0.000%

    No Known Activations