© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1611
    Prev
    Next
    INDEX
    Explanations

    allowing oneself to feel emotions

    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
    𒀊
    2.42
    च्युअल
    2.39
    訸
    2.31
     Küçük
    2.31
     Ettha
    2.30
     deuxième
    2.29
     následuj
    2.29
     sogenannten
    2.27
    𒆷
    2.27
     folgenden
    2.27
    POSITIVE LOGITS
     and
    2.62
    ,
    2.50
     in
    2.46
    .
    2.33
     is
    2.32
     has
    2.29
     the
    2.25
     with
    2.24
     from
    2.18
     to
    2.14
    Activations Density 0.046%

    No Known Activations