Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 69
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    ,
    0.89
    is
    0.71
    usions
    0.57
     discomfort
    0.57
     can
    0.56
    й
    0.56
    ction
    0.55
    ),
    0.55
    istics
    0.55
     tremendous
    0.55
    POSITIVE LOGITS
     وبين
    0.84
    AKS
    0.78
    URDAY
    0.77
    ἆ
    0.74
     إليها
    0.70
    ে
    0.70
    ఎస్‌
    0.69
    ECs
    0.69
    ᓃ
    0.69
     raíces
    0.67
    Activations Density 6.252%

    No Known Activations