© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12696
    Prev
    Next
    INDEX
    Explanations

    like air and metallic scents

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝘁
    1.39
    tem
    1.25
    ỡ
    1.20
    chen
    1.20
     번째
    1.19
    der
    1.18
    ting
    1.17
    𝗽
    1.17
    ther
    1.13
    wärts
    1.13
    POSITIVE LOGITS
     amenaza
    1.78
     amenazas
    1.50
     multicolored
    1.50
    “”
    1.48
     amea
    1.47
     barcodes
    1.47
     warranties
    1.45
     угро
    1.45
     barbarian
    1.45
     Helvetica
    1.44
    Activations Density 0.000%

    No Known Activations