© 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. 45137
    Prev
    Next
    INDEX
    Explanations

    forfeitures

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

    SQL injection input

    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
    сур
    0.49
    Od
    0.47
    Pile
    0.47
    Кла
    0.47
    🥬
    0.47
    🛖
    0.46
    Кар
    0.46
    Likes
    0.46
    Probe
    0.46
    Т
    0.46
    POSITIVE LOGITS
     शारीरिक
    0.49
     migratory
    0.48
     unfore
    0.47
     schwier
    0.47
     stormed
    0.46
    ])))
    0.46
    ９
    0.46
     unprocessed
    0.45
     ország
    0.45
     italic
    0.44
    Activations Density 0.000%

    No Known Activations