© 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. 8111
    Prev
    Next
    INDEX
    Explanations

    exponentiation, equations, identity

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

    The neuron activates strongly on numeric tokens—especially floating‐point or other multi‐digit numbers.

    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
    {$
    0.72
    },
    0.67
     },
    0.62
     }_{
    0.62
    ց
    0.59
    }{$
    0.58
     {:.
    0.58
    现金
    0.58
     earnings
    0.57
    |}
    0.57
    POSITIVE LOGITS
    identical
    0.63
     identiques
    0.59
     Conflicts
    0.58
     Chambers
    0.55
     behö
    0.55
     natthi
    0.55
     identique
    0.55
     identical
    0.53
     indist
    0.52
    谍
    0.52
    Activations Density 0.000%

    No Known Activations