© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5376
    Prev
    Next
    INDEX
    Explanations

    active listening and summarizing

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     trajectory
    0.71
     bankruptcy
    0.69
     football
    0.66
     deterministic
    0.66
     gradual
    0.65
     irreversible
    0.63
     inaug
    0.62
     ramping
    0.62
     k
    0.62
     perman
    0.62
    POSITIVE LOGITS
    तिरिक्त
    0.86
    áveis
    0.82
    plus
    0.82
     extras
    0.81
    точ
    0.81
    ILABLE
    0.81
    鿆
    0.80
    minster
    0.80
     เศษ
    0.78
     sociis
    0.78
    Activations Density 0.075%

    No Known Activations