© 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. 13966
    Prev
    Next
    INDEX
    Explanations

    languages, translation, code, technical descriptions

    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
     женщина
    1.42
     活動
    1.39
     歩
    1.38
    選手
    1.32
    在前
    1.32
     店舗
    1.31
    正月
    1.24
    在中
    1.23
    病人
    1.21
    แต่ง
    1.21
    POSITIVE LOGITS
     spectacular
    1.32
     realities
    1.26
     increasingly
    1.21
     understandable
    1.18
     rightful
    1.17
     magnificent
    1.16
     incredibly
    1.15
     grotesque
    1.15
     fantastic
    1.13
     ultimate
    1.13
    Activations Density 0.575%

    No Known Activations