© 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. 11132
    Prev
    Next
    INDEX
    Explanations

    repeating actions or phrases

    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
    em
    3.02
    ゅう
    2.27
    ermis
    2.21
    翘
    2.19
    emi
    2.17
    Em
    2.07
    mitt
    2.03
    embr
    2.02
    won
    2.00
     em
    1.96
    POSITIVE LOGITS
    एस
    2.84
    ঙালি
    2.71
     Ради
    2.44
    𝓼
    2.44
    蔔
    2.41
    তা
    2.33
     方
    2.32
    敷
    2.31
    。\
    2.31
    acycl
    2.28
    Activations Density 0.011%

    No Known Activations