© 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. 5957
    Prev
    Next
    INDEX
    Explanations

    todays date

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

    The neuron activates on multi‐digit numeric tokens (including decimals and long 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
     जल्
    0.56
    মনের
    0.53
     படைய
    0.53
     कह
    0.52
     ś
    0.52
     dí
    0.52
     நீர்
    0.51
     hrá
    0.50
    ಥ
    0.50
    ందం
    0.49
    POSITIVE LOGITS
    楸
    0.54
    ᾿
    0.52
     versionName
    0.50
    वाल
    0.48
    ாய
    0.47
     คะ
    0.47
    移植
    0.47
    عبير
    0.46
     Vereinig
    0.45
     حوالي
    0.44
    Activations Density 0.368%

    No Known Activations