© 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. 13185
    Prev
    Next
    INDEX
    Explanations

    tips and advice

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

    The neuron activates strongly on occurrences of the word “tip” (or “Tip”) used as a section heading or call‐out label.

    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
     impianti
    0.63
     Dá
    0.58
     Вер
    0.57
     எஸ்
    0.56
     ඇ
    0.55
     assessing
    0.55
     ဒါ
    0.55
    எஸ்
    0.54
     Width
    0.53
     κό
    0.53
    POSITIVE LOGITS
     tip
    1.07
    Tip
    0.98
     tipped
    0.94
    팁
    0.92
     Tip
    0.91
     tipping
    0.91
    tipped
    0.90
     tips
    0.86
     Tipp
    0.85
     tipp
    0.85
    Activations Density 0.139%

    No Known Activations