© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5286
    Prev
    Next
    INDEX
    Explanations

    what's truly important or matters

    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
     fem
    0.61
    }}{
    0.61
    辣
    0.61
    dV
    0.59
    洄
    0.58
    eda
    0.58
     виде
    0.57
    Eo
    0.57
    铃
    0.56
    tega
    0.55
    POSITIVE LOGITS
     matters
    0.76
     questione
    0.76
     matter
    0.73
     miserable
    0.72
     શોધ
    0.70
     unimportant
    0.67
     uncomfortable
    0.66
     Matters
    0.66
    ORG
    0.66
     jums
    0.65
    Activations Density 0.064%

    No Known Activations