© 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. 6964
    Prev
    Next
    INDEX
    Explanations

    incredibly followed by descriptors

    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
    scatterplot
    0.89
    ienda
    0.85
    ྞ
    0.84
    ྕ
    0.84
     かわ
    0.84
    㩴
    0.83
     اخت
    0.82
    ᕋ
    0.81
    ྵ
    0.81
    }}}=
    0.81
    POSITIVE LOGITS
     When
    0.83
     And
    0.79
     Fill
    0.76
     and
    0.75
     Can
    0.74
     heart
    0.74
     Filing
    0.73
     Starting
    0.71
     Shop
    0.71
     Fly
    0.70
    Activations Density 0.205%

    No Known Activations