© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2651
    Prev
    Next
    INDEX
    Explanations

    consult with

    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_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    alkyl
    1.76
    genheim
    1.71
    secutive
    1.60
    teen
    1.55
     세제곱
    1.55
    ths
    1.53
    stufe
    1.53
    bilder
    1.51
     %,
    1.50
     outgrowth
    1.49
    POSITIVE LOGITS
     Liam
    1.96
     Colin
    1.89
     Krzysz
    1.80
     Marco
    1.79
     Hickey
    1.79
     Jad
    1.73
     Vincent
    1.73
     Garr
    1.72
     Sasha
    1.72
     Darryl
    1.70
    Activations Density 0.033%

    No Known Activations