© 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. 127874
    Prev
    Next
    INDEX
    Explanations

    relating to definitions or concepts

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

    SQL injection

    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
    एम
    0.55
    М
    0.55
    Princess
    0.55
    Aless
    0.53
    5
    0.53
    뭘
    0.53
    1
    0.52
    Recommended
    0.52
    7
    0.52
    Japan
    0.51
    POSITIVE LOGITS
    溶液
    0.49
     n
    0.47
     zhōng
    0.46
    魂
    0.44
     Solutions
    0.43
    引导
    0.43
    沉
    0.42
     galvan
    0.42
     hudson
    0.41
     offsetY
    0.41
    Activations Density 0.000%

    No Known Activations