© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15123
    Prev
    Next
    INDEX
    Explanations

    encoded strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     χ
    0.79
    த்தைக்
    0.71
     синте
    0.71
     diminishes
    0.70
     ног
    0.70
    LAGAB
    0.70
     ре
    0.69
     ἀ
    0.68
     чувства
    0.67
     такой
    0.67
    POSITIVE LOGITS
    Long
    0.80
    Z
    0.79
    z
    0.73
    j
    0.73
    Q
    0.73
    Job
    0.71
    Dot
    0.71
    Environmental
    0.71
    J
    0.71
    Team
    0.71
    Activations Density 0.025%

    No Known Activations