© 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. 41-GEMMASCOPE-2-RES-65K
    7. 15375
    Prev
    Next
    INDEX
    Explanations

    say "blood"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     оре
    0.59
    ラッピング
    0.52
    🛸
    0.51
    🐢
    0.50
    蒽
    0.50
    यिक
    0.50
    ⛅
    0.49
    Fernando
    0.48
    尒
    0.47
    栈
    0.47
    POSITIVE LOGITS
     blood
    5.59
     Blood
    5.16
     BLOOD
    5.13
    blood
    5.09
    Blood
    5.09
    血
    4.94
     sangue
    4.63
    血液
    4.53
     blod
    4.44
     sangre
    4.41
    Activations Density 0.096%

    No Known Activations