© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6582
    Prev
    Next
    INDEX
    Explanations

    us/therapists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     so
    1.61
    so
    1.22
    So
    1.21
     since
    1.18
     так
    1.12
     tantas
    1.10
     because
    1.08
     So
    1.07
    s
    1.06
     kerana
    1.06
    POSITIVE LOGITS
     naturally
    1.40
    当然
    1.30
     সহজেই
    1.26
    必然
    1.21
     forcément
    1.20
    不必
    1.19
    不得
    1.16
    obviously
    1.14
     स्वाभाविक
    1.13
    也就是说
    1.10
    Activations Density 0.204%

    No Known Activations