© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8391
    Prev
    Next
    INDEX
    Explanations

    because of

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags causal or explanatory discourse markers (e.g. “Because,” “Since,” “because of,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    因为
    1.56
    因為
    1.44
     because
    1.34
     porque
    1.29
     karena
    1.28
     pretože
    1.28
    它
    1.27
     ponieważ
    1.27
     protože
    1.26
     deoarece
    1.25
    POSITIVE LOGITS
     of
    0.93
    ir
    0.90
    u
    0.85
    although
    0.85
     appunto
    0.84
    ur
    0.77
    uot
    0.77
    ve
    0.76
    of
    0.76
    ructured
    0.75
    Activations Density 0.095%

    No Known Activations