© 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. 16-GEMMASCOPE-2-RES-262K
    7. 43172
    Prev
    Next
    INDEX
    Explanations

    SSTI injection and change

    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_16_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
     유리
    0.57
    дне
    0.56
     폭
    0.52
     XS
    0.52
     breadth
    0.50
    abyrinth
    0.50
     equator
    0.50
     hydrophilic
    0.48
     superficies
    0.48
     suelo
    0.48
    POSITIVE LOGITS
    İ
    0.51
    UPDATE
    0.47
    Writes
    0.46
    Row
    0.45
    Мак
    0.45
    Neighbors
    0.44
    Signing
    0.44
    Modules
    0.43
    Declaration
    0.43
    Update
    0.43
    Activations Density 0.000%

    No Known Activations