© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7920
    Prev
    Next
    INDEX
    Explanations

    sexual assault/domestic violence hotline information

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

    The neuron fires on sequences of hexadecimal digits (e.g., long hex strings or identifiers).

    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
    म्ह
    0.60
     เด
    0.58
     ク
    0.58
    ﻤ
    0.58
     Сле
    0.57
     Россию
    0.56
     或者
    0.55
     영국
    0.55
     ഡ
    0.55
    Lauren
    0.55
    POSITIVE LOGITS
     data
    0.54
     competence
    0.49
     directives
    0.49
     audiov
    0.49
     hemodynamic
    0.48
     responsabilità
    0.48
     directive
    0.48
     be
    0.48
     transactions
    0.48
     information
    0.47
    Activations Density 0.040%

    No Known Activations