© 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-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3020
    Prev
    Next
    INDEX
    Explanations

    asking about what's going on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
    TextMesh
    0.78
     домаћинстава
    0.77
    ޚ
    0.76
     ஆய
    0.75
     Encyclopædia
    0.74
    JSPA
    0.73
     shifting
    0.72
     الساعه
    0.72
    avises
    0.71
    iffany
    0.71
    POSITIVE LOGITS
    iko
    0.64
     through
    0.59
    zien
    0.58
    ດ້ວຍ
    0.57
    ;
    0.57
    पट
    0.57
     cuanto
    0.56
     antennes
    0.56
    iken
    0.56
    ites
    0.56
    Activations Density 0.029%

    No Known Activations