© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1545
    Prev
    Next
    INDEX
    Explanations

    invade or steal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ہو۔
    0.48
     sikker
    0.46
     yields
    0.45
     aiutare
    0.45
     aiuta
    0.44
    ៊
    0.44
     nettement
    0.44
     terken
    0.44
    艰
    0.44
     cryptographic
    0.41
    POSITIVE LOGITS
     invade
    0.91
     stealing
    0.85
     infiltrate
    0.84
     infiltr
    0.82
     stole
    0.80
     threaten
    0.79
     steal
    0.77
     steals
    0.76
     infiltrating
    0.75
     encroach
    0.75
    Activations Density 0.008%

    No Known Activations