© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3476
    Prev
    Next
    INDEX
    Explanations

    specially programmed or designed

    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
    ↵
    1.39
    </em>
    1.20
    the
    1.17
     the
    1.01
    am
    0.96
     sozial
    0.94
    ні
    0.92
     gateway
    0.92
    </h3>
    0.91
     place
    0.90
    POSITIVE LOGITS
    يل
    0.98
    jší
    0.92
     Increases
    0.88
    ifier
    0.83
     postérieurs
    0.83
     Medications
    0.81
    nger
    0.80
    ක්
    0.80
     specially
    0.79
    lier
    0.79
    Activations Density 0.001%

    No Known Activations