© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113537
    Prev
    Next
    INDEX
    Explanations

    vulnerability, exploits

    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/layer_31_width_262k_l0_medium
    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
    irk
    0.50
    ada
    0.49
    orders
    0.49
     насе
    0.47
    ราว
    0.45
    <0x94>
    0.44
    opening
    0.44
     organisasi
    0.44
     ada
    0.43
     oxidized
    0.43
    POSITIVE LOGITS
     Spaß
    0.47
    Corruption
    0.44
    Louisiana
    0.43
     thérapeutique
    0.43
    Luxury
    0.43
    守
    0.43
    "`
    0.42
     bribery
    0.42
    道路
    0.42
    Gard
    0.42
    Activations Density 0.000%

    No Known Activations