© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5014
    Prev
    Next
    INDEX
    Explanations

    more / less than

    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_17_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
    ↵↵
    0.79
     compare
    0.78
     en
    0.76
      
    0.71
    dis
    0.69
     dis
    0.68
     relative
    0.68
     sub
    0.66
     away
    0.65
    Is
    0.65
    POSITIVE LOGITS
     LOCCTR
    1.13
    𒊕
    1.05
     tcpHeader
    1.03
    ównie
    1.03
    <unused1618>
    1.03
     glTex
    1.02
    avacako
    1.02
     sasane
    1.01
     threx
    1.01
     mTOR
    1.01
    Activations Density 0.061%

    No Known Activations