© 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. 3479
    Prev
    Next
    INDEX
    Explanations

    treatment options and recommendations

    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
    řej
    1.56
    mart
    1.36
    ン
    1.33
    rzej
    1.30
    edTest
    1.30
    érard
    1.29
    らの
    1.28
    zież
    1.27
    ય
    1.27
    oleč
    1.26
    POSITIVE LOGITS
     goofy
    1.61
     ridiculously
    1.55
     vibes
    1.53
     newbie
    1.45
     bo
    1.45
     instinctive
    1.41
     sexy
    1.41
     wacky
    1.40
     angelic
    1.40
     fantastical
    1.39
    Activations Density 0.208%

    No Known Activations