© 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
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5559
    Prev
    Next
    INDEX
    Explanations

    social demographics and identity groups

    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_24_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
    ։
    0.50
    ।
    0.50
    ا۔
    0.50
    。
    0.49
    IPLE
    0.46
    "/>.
    0.44
    ☇
    0.44
    |$.
    0.42
    くて
    0.42
     ול
    0.42
    POSITIVE LOGITS
     opponents
    0.59
     companies
    0.56
     kanssa
    0.53
     sociétés
    0.52
     insurers
    0.51
     firms
    0.50
     कंपनियां
    0.50
     museums
    0.49
    companies
    0.48
     సినిమాలు
    0.48
    Activations Density 0.008%

    No Known Activations