© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7956
    Prev
    Next
    INDEX
    Explanations

    shapes and roundness like bulleted, pebble, diamond

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

    The neuron activates on tokens that are concrete, physical object nouns (e.g. “ball,” “brick,” “diamond,” “snow globe,” “Flower,” 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
    充满
    0.63
    -]+
    0.57
    encana
    0.54
    ဝန်
    0.54
    好友
    0.54
    いました
    0.53
    ป่วย
    0.52
    充滿
    0.52
    سيط
    0.52
    +}$,
    0.51
    POSITIVE LOGITS
     shaped
    0.92
     Shaped
    0.77
    状
    0.77
    shaped
    0.72
     crusher
    0.65
    iness
    0.64
     drilled
    0.63
     orchard
    0.62
     paved
    0.61
     barbec
    0.61
    Activations Density 0.447%

    No Known Activations