© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15463
    Prev
    Next
    INDEX
    Explanations

    public followed by keywords

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

    The neuron is selectively activating on occurrences of the substring “public” (e.g. in URLs or standalone).

    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
    К
    1.41
    IT
    1.36
    RA
    1.25
    AK
    1.13
    อาจ
    1.13
    AD
    1.12
    RE
    1.09
    的情
    1.09
    です
    1.08
    K
    1.08
    POSITIVE LOGITS
    aklar
    1.25
    zione
    1.16
    ic
    1.14
    రుగులు
    1.08
    ième
    1.07
     Особенно
    1.05
    
    1.05
    amag
    1.01
    ні
    1.00
    lié
    1.00
    Activations Density 0.000%

    No Known Activations