© 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. 18753
    Prev
    Next
    INDEX
    Explanations

    incrementing and adding

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

    arithmetic addition and assignment

    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
    ucked
    0.50
    nese
    0.50
    rift
    0.46
    âtre
    0.46
    hty
    0.45
    nie
    0.44
    rique
    0.44
    ध
    0.42
    rons
    0.42
    raž
    0.42
    POSITIVE LOGITS
    力和
    0.48
    也要
    0.46
     ulteriori
    0.45
    与
    0.44
     "\
    0.44
    委員
    0.43
    闲
    0.43
     이번
    0.41
     અને
    0.41
    面前
    0.41
    Activations Density 0.000%

    No Known Activations