© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1094
    Prev
    Next
    INDEX
    Explanations

    share, business, cloud, software, Mario

    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_17_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
     S
    0.67
    age
    0.66
     Covid
    0.66
     Qu
    0.66
    0.65
     Stein
    0.64
     Pol
    0.64
     Pedro
    0.64
     Lie
    0.64
     Corona
    0.62
    POSITIVE LOGITS
     হইবার
    1.25
    গ্
    1.17
    𒋗
    1.12
    सिले
    1.09
     linkCell
    1.08
    ஃப
    1.06
     outflow
    1.06
     ହ
    1.05
     mekanisme
    1.03
     움직
    1.03
    Activations Density 0.587%

    No Known Activations