© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    the start of responses

    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
     त्यांचे
    0.74
     adapts
    0.73
     त्यांचा
    0.73
    ahy
    0.71
     inspires
    0.71
     gets
    0.69
     तिचा
    0.69
     draws
    0.68
    荒
    0.68
    ◼
    0.68
    POSITIVE LOGITS
     located
    1.28
     situated
    1.16
     ubicada
    1.16
     avven
    1.13
     ubic
    1.11
     PRIOR
    1.11
     située
    1.10
     forthwith
    1.07
     commencing
    1.06
     localizado
    1.04
    Activations Density 0.094%

    No Known Activations