© 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. 3985
    Prev
    Next
    INDEX
    Explanations

    requesting specifics about context

    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
     mapDispatch
    2.40
    عاد
    2.27
    clickable
    2.23
    베
    2.17
     принци
    2.16
    ет
    2.14
    姑
    2.14
    ើ
    2.12
    er
    2.11
    clicked
    2.10
    POSITIVE LOGITS
     recorders
    2.21
     recorder
    2.20
     foss
    2.04
     domest
    1.96
     Recording
    1.84
    ጊዜ
    1.84
     précieux
    1.76
     Recorder
    1.76
    स्तर
    1.74
     avven
    1.71
    Activations Density 0.259%

    No Known Activations