© 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. 5199
    Prev
    Next
    INDEX
    Explanations

    forests, brooks, and vales

    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
     dyn
    0.76
     pulver
    0.75
     stora
    0.74
     certifies
    0.74
     depos
    0.73
     databases
    0.73
     awesome
    0.71
     싸
    0.71
     crunchy
    0.70
     قبضہ
    0.69
    POSITIVE LOGITS
    brook
    0.93
    wood
    0.88
     Creek
    0.85
     Brook
    0.84
    Woods
    0.83
    bridge
    0.82
    field
    0.82
    ton
    0.80
     Pines
    0.80
    vale
    0.80
    Activations Density 0.162%

    No Known Activations