© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2190
    Prev
    Next
    INDEX
    Explanations

    recursive heuristic inverse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    äv
    0.45
    ievers
    0.44
    ionar
    0.42
    ?’”
    0.42
     Etiam
    0.42
    .’”
    0.42
    <unused1096>
    0.41
     Marquette
    0.41
    rauen
    0.41
    iorari
    0.41
    POSITIVE LOGITS
     NDVI
    0.30
     iterating
    0.28
      
    0.28
     different
    0.27
     recursive
    0.27
     biomass
    0.26
     infinite
    0.26
     heuristic
    0.26
     зна
    0.25
     inverse
    0.25
    Activations Density 0.356%

    No Known Activations