© 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. 29342
    Prev
    Next
    INDEX
    Explanations

    cage fire

    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
    دا
    0.78
     أنّ
    0.75
    {
    0.75
     aportar
    0.75
    .
    0.75
    -
    0.74
    ität
    0.74
     enfrentar
    0.74
     analizar
    0.73
     avanzar
    0.73
    POSITIVE LOGITS
     From
    0.93
    ので
    0.88
     Ս
    0.87
    ри
    0.86
    </h2>
    0.85
    να
    0.80
    of
    0.78
    क
    0.78
    </h3>
    0.76
    k
    0.75
    Activations Density 0.002%

    No Known Activations