© 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. 24-GEMMASCOPE-2-RES-16K
    4. 7016
    Prev
    Next
    INDEX
    Explanations

    programming code separators

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

    The neuron fires strongly on list-style separators—especially semicolons (and other punctuation marks used to break up enumerations).

    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_24_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
    ه
    1.77
    ز
    1.66
    ्य
    1.63
    ة
    1.63
    }";
    1.57
    ب
    1.53
    ב
    1.52
    ्ले
    1.52
    }");
    1.50
    ため
    1.49
    POSITIVE LOGITS
    ée
    1.50
    然而
    1.39
    ır
    1.38
    此外
    1.34
    tı
    1.32
    otted
    1.28
    𝕟
    1.28
    irt
    1.27
     بنابراین
    1.23
    ard
    1.21
    Activations Density 0.114%

    No Known Activations