© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14920
    Prev
    Next
    INDEX
    Explanations

    Volume

    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
    chés
    0.57
    साद
    0.56
    জীবন
    0.55
     ईमान
    0.52
    莎
    0.52
     candidacy
    0.50
    汀
    0.49
    笑着
    0.49
    פל
    0.49
    正直
    0.48
    POSITIVE LOGITS
     vol
    2.22
     Vol
    2.11
     Volume
    2.02
     volume
    1.93
     VOLUME
    1.92
    Volume
    1.86
    volume
    1.83
     VOL
    1.80
    Vol
    1.80
     volumen
    1.79
    Activations Density 0.115%

    No Known Activations