© 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. 7-GEMMASCOPE-2-RES-16K
    7. 865
    Prev
    Next
    INDEX
    Explanations

    help/

    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
    e
    2.43
    훑
    2.33
    gr
    2.31
    ة
    2.19
    ed
    2.13
    tie
    2.11
    eid
    2.10
    eem
    2.09
    ಿಂತ
    2.08
    emis
    2.06
    POSITIVE LOGITS
    ्य
    2.84
     financière
    2.75
     solvers
    2.66
    leistungen
    2.61
    果た
    2.57
    вати
    2.53
    !/"
    2.47
     Versorgung
    2.46
     GetAll
    2.44
     consequatur
    2.44
    Activations Density 1.479%

    No Known Activations