© 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. 420
    Prev
    Next
    INDEX
    Explanations

    ADTs, mechanisms, stability, adaptation

    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
     mistaken
    0.43
    -
    0.43
     ใน
    0.43
     solar
    0.43
    直し
    0.42
     worth
    0.41
     тут
    0.41
    始め
    0.41
     appears
    0.41
    還有
    0.40
    POSITIVE LOGITS
     muitas
    0.60
    Ⲕ
    0.59
     detalhes
    0.57
     mecanismos
    0.56
    Ⲟ
    0.55
    Ꮐ
    0.55
     processos
    0.54
     resultante
    0.53
     fatores
    0.53
    Ꮢ
    0.53
    Activations Density 0.464%

    No Known Activations