© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3414
    Prev
    Next
    INDEX
    Explanations

    push-ups

    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
    Not in Any Lists

    No Comments

    Negative Logits
    。（
    1.68
     prepd
    1.54
    。(
    1.53
    Rn
    1.50
    ́u
    1.45
    ンの
    1.45
    Scorch
    1.44
    。[
    1.44
    
    1.43
    Missense
    1.43
    POSITIVE LOGITS
     Tar
    1.50
     Har
    1.44
     Gal
    1.36
     Col
    1.34
     P
    1.34
     Dul
    1.32
     Ze
    1.32
     Lux
    1.30
     Dil
    1.29
     Rem
    1.29
    Activations Density 0.330%

    No Known Activations