© 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. 2576
    Prev
    Next
    INDEX
    Explanations

    pointer arithmetic

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

    C and C++ code snippets

    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
    觀塘
    0.69
     concierge
    0.68
     keltiradi
    0.66
     पार्टनर
    0.65
    覽
    0.64
     Tjiwarl
    0.64
    銀座
    0.64
    癢
    0.64
    香り
    0.64
    獎
    0.64
    POSITIVE LOGITS
     printf
    1.01
     scanf
    1.01
     ifstream
    0.99
     getchar
    0.97
    printf
    0.96
     fprintf
    0.96
     pthread
    0.96
    CurrentByte
    0.95
    ofstream
    0.95
    Malloc
    0.95
    Activations Density 0.005%

    No Known Activations