© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    father and husband

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

    the presence of blog‐post metadata labels (e.g. “published,” “by,” “in,” “category,” “tagged,” etc.).

    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
     FOUND
    0.90
    elig
    0.78
     границ
    0.75
    욱
    0.74
    Tokenizer
    0.73
     الأصفر
    0.73
    dueDate
    0.72
     э
    0.72
    xRt
    0.72
     Дэ
    0.71
    POSITIVE LOGITS
    ারে
    0.82
     growths
    0.77
    បញ្ចូល
    0.74
     modifica
    0.73
    தல
    0.70
    from
    0.70
    除
    0.70
    ât
    0.69
    嫩
    0.68
     Công
    0.68
    Activations Density 0.000%

    No Known Activations