© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2210
    Prev
    Next
    INDEX
    Explanations

    after you brushed your teeth

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

    The neuron detects technical terms and commands related to software build and version‐control operations (e.g., build, clean, checkout, update).

    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
    .).
    1.74
    ++.
    1.45
    '.
    1.45
    ().
    1.42
    ].
    1.41
    .</
    1.41
    ).
    1.41
    }.
    1.38
    。
    1.38
     ).
    1.37
    POSITIVE LOGITS
    !;
    1.20
     بنائیں
    1.14
    ?;
    1.11
    ;
    1.10
    ပါတယ်
    1.08
    ራል
    1.05
    ራሉ
    0.98
    ?/
    0.92
     گئیں
    0.87
    ”）
    0.87
    Activations Density 0.028%

    No Known Activations