© 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. 4300
    Prev
    Next
    INDEX
    Explanations

    where to find

    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
     Islas
    0.74
    릅
    0.67
     共
    0.66
     participated
    0.66
     participation
    0.65
     Participation
    0.65
    Participation
    0.62
     clogging
    0.61
    wc
    0.61
    Ꮧ
    0.60
    POSITIVE LOGITS
     found
    1.38
     finding
    1.27
     find
    1.26
     obtained
    1.25
     obtain
    1.20
     finds
    1.17
    find
    1.16
    Find
    1.16
    found
    1.15
    Finding
    1.10
    Activations Density 0.441%

    No Known Activations