© 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. 11300
    Prev
    Next
    INDEX
    Explanations

    defining concepts or features

    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
    嗘
    2.95
    場合
    2.68
    unch
    2.52
    ạn
    2.47
     नाना
    2.42
     HY
    2.40
    voud
    2.38
     "'
    2.37
    嗕
    2.31
    Ւ
    2.30
    POSITIVE LOGITS
    氓
    2.71
    ampuan
    2.53
    ников
    2.33
    antren
    2.24
     instilled
    2.24
    沤
    2.16
    ິກ
    2.15
    minster
    2.15
     functioning
    2.14
     न्याया
    2.14
    Activations Density 0.010%

    No Known Activations