© 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. 31-GEMMASCOPE-2-RES-262K
    7. 83058
    Prev
    Next
    INDEX
    Explanations

    international languages adversarial

    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
    b
    0.49
    Nev
    0.41
    ine
    0.41
    izo
    0.40
    .
    0.40
    B
    0.40
    <b>
    0.40
     e
    0.39
    Native
    0.39
     gum
    0.39
    POSITIVE LOGITS
    腦
    0.57
    加以
    0.54
    毆
    0.53
    pgMove
    0.53
     ਮੰ
    0.52
     estím
    0.52
    اظ
    0.52
    ędzynarod
    0.51
    äser
    0.51
    aeskeygenassist
    0.50
    Activations Density 0.004%

    No Known Activations