© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2523
    Prev
    Next
    INDEX
    Explanations

    modular design

    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
    ंड
    0.74
    তি
    0.74
    iceps
    0.68
    మాట
    0.67
    еро
    0.66
    সের
    0.66
    ο
    0.64
    บ
    0.64
    𝓷
    0.63
    ட்ட
    0.63
    POSITIVE LOGITS
     nature
    1.64
    nature
    1.37
     Nature
    1.27
     natures
    1.26
    Nature
    1.16
     NATURE
    1.03
     naturaleza
    1.01
     natureza
    0.96
     தன்மை
    0.95
    natures
    0.87
    Activations Density 0.571%

    No Known Activations